default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDHung-yi Lee
Hung-Yi Lee
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[j27]Shu-Wen Yang
, Heng-Jui Chang, Zili Huang, Andy T. Liu, Cheng-I Lai, Haibin Wu, Jiatong Shi, Xuankai Chang, Hsiang-Sheng Tsai, Wen-Chin Huang, Tzu-hsun Feng, Po-Han Chi, Yist Y. Lin, Yung-Sung Chuang, Tzu-Hsien Huang, Wei-Cheng Tseng, Kushal Lakhotia, Shang-Wen Li, Abdelrahman Mohamed, Shinji Watanabe, Hung-yi Lee:
A Large-Scale Evaluation of Speech Foundation Models. IEEE ACM Trans. Audio Speech Lang. Process. 32: 2884-2899 (2024)- [j26]Kai-Wei Chang, Haibin Wu, Yu-Kai Wang, Yuan-Kuei Wu, Hua Shen, Wei-Cheng Tseng, Iu-thing Kang, Shang-wen Li, Hung-Yi Lee:
SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks. IEEE ACM Trans. Audio Speech Lang. Process. 32: 3730-3744 (2024) - [j25]Shensian Syu, Juncheng Xie, Hung-yi Lee:
Improving Non-Autoregressive Translation Quality With Pretrained Language Model, Embedding Distillation and Upsampling Strategy for CTC. IEEE ACM Trans. Audio Speech Lang. Process. 32: 4121-4133 (2024) - [c223]Cheng-Han Chiang, Hung-yi Lee:
Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations. ACL (Findings) 2024: 2734-2751 - [c222]Guan-Ting Lin, Cheng-Han Chiang, Hung-yi Lee:
Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations. ACL (1) 2024: 6626-6642 - [c221]Haibin Wu, Ho-Lam Chung, Yi-Cheng Lin, Yuan-Kuei Wu, Xuanjun Chen, Yu-Chi Pai, Hsiu-Hsuan Wang, Kai-Wei Chang, Alexander H. Liu, Hung-yi Lee:
Codec-SUPERB: An In-Depth Analysis of Sound Codec Models. ACL (Findings) 2024: 10330-10348 - [c220]Shih-Cheng Huang, Pin-Zu Li, Yu-Chi Hsu, Kuang-Ming Chen, Yu-Tung Lin, Shih-Kai Hsiao, Richard Tzong-Han Tsai, Hung-yi Lee:
Chat Vector: A Simple Approach to Equip LLMs with Instruction Following and Model Alignment in New Languages. ACL (1) 2024: 10943-10959 - [c219]Siddhant Arora, Ankita Pasad, Chung-Ming Chien, Jionghao Han, Roshan S. Sharma, Jee-weon Jung, Hira Dhamyal, William Chen, Suwon Shon, Hung-yi Lee, Karen Livescu, Shinji Watanabe:
On the Evaluation of Speech Foundation Models for Spoken Language Understanding. ACL (Findings) 2024: 11923-11938 - [c218]Cheng-Han Chiang, Hung-yi Lee:
Over-Reasoning and Redundant Calculation of Large Language Models. EACL (2) 2024: 161-169 - [c217]Zhi Rui Tam, Cheng-Kuang Wu, Yi-Lin Tsai, Chieh-Yen Lin, Hung-yi Lee, Yun-Nung Chen:
Let Me Speak Freely? A Study On The Impact Of Format Restrictions On Large Language Model Performance. EMNLP (Industry Track) 2024: 1218-1236 - [c216]Cheng-Kuang Wu, Zhi Rui Tam, Chao-Chung Wu, Chieh-Yen Lin, Hung-yi Lee, Yun-Nung Chen:
I Need Help! Evaluating LLM's Ability to Ask for Users' Support: A Case Study on Text-to-SQL Generation. EMNLP 2024: 2191-2199 - [c215]Cheng-Han Chiang, Wei-Chih Chen, Chun-Yi Kuan, Chienchou Yang, Hung-yi Lee:
Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course. EMNLP 2024: 2489-2513 - [c214]Hsuan Su, Hua Farn, Fan-Yun Sun, Shang-Tse Chen, Hung-yi Lee:
Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition. EMNLP 2024: 8905-8915 - [c213]Guan-Ting Lin, Hung-yi Lee:
Can LLMs Understand the Implication of Emphasized Sentences in Dialogue? EMNLP (Findings) 2024: 13391-13401 - [c212]Hung-Ting Su, Ya-Ching Hsu, Xudong Lin, Xiang Qian Shi, Yulei Niu, Han-Yuan Hsu, Hung-yi Lee, Winston H. Hsu:
Unveiling Narrative Reasoning Limits of Large Language Models with Trope in Movie Synopses. EMNLP (Findings) 2024: 14839-14854 - [c211]Tzu-Han Lin, Chen-An Li, Hung-yi Lee, Yun-Nung Chen:
DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging. EMNLP 2024: 15506-15524 - [c210]Guan-Ting Lin, Wei Huang, Hung-yi Lee:
Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy Speech. EMNLP 2024: 20003-20015 - [c209]Hsuan-Fu Wang, Yi-Jen Shih, Heng-Jui Chang, Layne Berry, Puyuan Peng, Hung-Yi Lee, Hsin-Min Wang, David Harwath:
SpeechCLIP+: Self-Supervised Multi-Task Representation Learning for Speech Via Clip and Speech-Image Data. ICASSP Workshops 2024: 465-469 - [c208]Fabian Ritter Gutierrez, Kuan-Po Huang, Dianwen Ng, Jeremy H. M. Wong, Hung-Yi Lee, Eng Siong Chng, Nancy F. Chen:
Noise Robust Distillation of Self-Supervised Speech Models via Correlation Metrics. ICASSP Workshops 2024: 495-499 - [c207]Chih-Kai Yang, Kuan-Po Huang, Ke-Han Lu, Chun-Yi Kuan, Chi-Yuan Hsiao, Hung-Yi Lee:
Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR And Speech-to-Text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision. ICASSP Workshops 2024: 540-544 - [c206]Hung-Chieh Fang, Nai-Xuan Ye, Yi-Jen Shih, Puyuan Peng, Hsuan-Fu Wang, Layne Berry, Hung-Yi Lee, David Harwath:
Integrating Self-Supervised Speech Model with Pseudo Word-Level Targets from Visually-Grounded Speech Model. ICASSP Workshops 2024: 645-649 - [c205]Tzu-Han Lin, How-Shing Wang, Hao-Yung Weng, Kuang-Chen Peng, Zih-Ching Chen, Hung-Yi Lee:
PEFT for Speech: Unveiling Optimal Placement, Merging Strategies, and Ensemble Techniques. ICASSP Workshops 2024: 705-709 - [c204]Haibin Wu, Heng-Cheng Kuo, Yu Tsao, Hung-Yi Lee:
Scalable Ensemble-Based Detection Method Against Adversarial Attacks For Speaker Verification. ICASSP 2024: 4670-4674 - [c203]Yuan Tseng, Layne Berry, Yiting Chen, I-Hsiang Chiu, Hsuan-Hao Lin, Max Liu, Puyuan Peng, Yi-Jen Shih, Hung-Yu Wang, Haibin Wu, Poyao Huang, Chun-Mao Lai, Shang-Wen Li, David Harwath, Yu Tsao, Abdelrahman Mohamed, Chi-Luen Feng, Hung-Yi Lee:
AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models. ICASSP 2024: 6890-6894 - [c202]Xuanjun Chen, Haibin Wu, Chung-Che Wang, Hung-Yi Lee, Jyh-Shing Roger Jang:
Multimodal Transformer Distillation for Audio-Visual Synchronization. ICASSP 2024: 7755-7759 - [c201]Kuan-Po Huang, Chih-Kai Yang, Yu-Kuan Fu, Ewan Dunbar, Hung-Yi Lee:
Zero Resource Code-Switched Speech Benchmark Using Speech Utterance Pairs for Multiple Spoken Languages. ICASSP 2024: 10006-10010 - [c200]Guan-Ting Lin, Prashanth Gurunath Shivakumar, Ankur Gandhe, Chao-Han Huck Yang, Yile Gu, Shalini Ghosh, Andreas Stolcke, Hung-Yi Lee, Ivan Bulyko:
Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue. ICASSP 2024: 10316-10320 - [c199]Chien-Yu Huang, Ke-Han Lu, Shih-Heng Wang, Chi-Yuan Hsiao, Chun-Yi Kuan, Haibin Wu, Siddhant Arora, Kai-Wei Chang, Jiatong Shi, Yifan Peng, Roshan S. Sharma, Shinji Watanabe, Bhiksha Ramakrishnan, Shady Shehata, Hung-Yi Lee:
Dynamic-Superb: Towards a Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark For Speech. ICASSP 2024: 12136-12140 - [c198]Chyi-Jiunn Lin, Guan-Ting Lin, Yung-Sung Chuang, Wei-Lun Wu, Shang-Wen Li, Abdelrahman Mohamed, Hung-Yi Lee, Lin-Shan Lee:
SpeechDPR: End-To-End Spoken Passage Retrieval For Open-Domain Spoken Question Answering. ICASSP 2024: 12476-12480 - [c197]Kevin Everson, Yile Gu, Chao-Han Huck Yang, Prashanth Gurunath Shivakumar, Guan-Ting Lin, Jari Kolehmainen, Ivan Bulyko, Ankur Gandhe, Shalini Ghosh, Wael Hamza, Hung-Yi Lee, Ariya Rastrow, Andreas Stolcke:
Towards ASR Robust Spoken Language Understanding Through in-Context Learning with Word Confusion Networks. ICASSP 2024: 12856-12860 - [c196]Shih-Cheng Huang, Shih-Heng Wang, Min-Han Shih, Saurav Sahay, Hung-yi Lee:
Systematic Analysis for Pretrained Language Model Priming for Parameter-Efficient Fine-tuning. NAACL (Student Research Workshop) 2024: 1-7 - [i274]Chih-Kai Yang, Kuan-Po Huang, Ke-Han Lu, Chun-Yi Kuan, Chi-Yuan Hsiao, Hung-yi Lee:
Investigating Zero-Shot Generalizability on Mandarin-English Code-Switched ASR and Speech-to-text Translation of Recent Foundation Models with Self-Supervision and Weak Supervision. CoRR abs/2401.00273 (2024) - [i273]Tzu-Han Lin, How-Shing Wang, Hao-Yung Weng, Kuang-Chen Peng, Zih-Ching Chen, Hung-yi Lee:
PEFT for Speech: Unveiling Optimal Placement, Merging Strategies, and Ensemble Techniques. CoRR abs/2401.02122 (2024) - [i272]Kevin Everson, Yile Gu, Chao-Han Huck Yang, Prashanth Gurunath Shivakumar, Guan-Ting Lin, Jari Kolehmainen, Ivan Bulyko, Ankur Gandhe, Shalini Ghosh, Wael Hamza, Hung-yi Lee, Ariya Rastrow, Andreas Stolcke:
Towards ASR Robust Spoken Language Understanding Through In-Context Learning With Word Confusion Networks. CoRR abs/2401.02921 (2024) - [i271]Chen-An Li, Hung-Yi Lee:
Examining Forgetting in Continual Pre-training of Aligned Large Language Models. CoRR abs/2401.03129 (2024) - [i270]David Cheng-Han Chiang, Hung-Yi Lee:
Over-Reasoning and Redundant Calculation of Large Language Models. CoRR abs/2401.11467 (2024) - [i269]Chyi-Jiunn Lin, Guan-Ting Lin, Yung-Sung Chuang, Wei-Lun Wu, Shang-Wen Li, Abdelrahman Mohamed, Hung-yi Lee, Lin-Shan Lee:
SpeechDPR: End-to-End Spoken Passage Retrieval for Open-Domain Spoken Question Answering. CoRR abs/2401.13463 (2024) - [i268]Wei-Ping Huang, Sung-Feng Huang, Hung-yi Lee:
Maximizing Data Efficiency for Cross-Lingual TTS Adaptation by Self-Supervised Representation Mixing and Embedding Initialization. CoRR abs/2402.01692 (2024) - [i267]Liang-Hsuan Tseng, En-Pei Hu, David Cheng-Han Chiang, Yuan Tseng, Hung-yi Lee, Lin-Shan Lee, Shao-Hua Sun:
REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR. CoRR abs/2402.03988 (2024) - [i266]David Cheng-Han Chiang, Hung-yi Lee:
Merging Facts, Crafting Fallacies: Evaluating the Contradictory Nature of Aggregated Factual Claims in Long-Form Generations. CoRR abs/2402.05629 (2024) - [i265]Hung-Chieh Fang, Nai-Xuan Ye, Yi-Jen Shih, Puyuan Peng, Hsuan-Fu Wang, Layne Berry, Hung-yi Lee, David Harwath:
Integrating Self-supervised Speech Model with Pseudo Word-level Targets from Visually-grounded Speech Model. CoRR abs/2402.05819 (2024) - [i264]Hsuan-Fu Wang, Yi-Jen Shih, Heng-Jui Chang, Layne Berry, Puyuan Peng, Hung-yi Lee, Hsin-Min Wang, David Harwath:
SpeechCLIP+: Self-supervised multi-task representation learning for speech via CLIP and speech-image data. CoRR abs/2402.06959 (2024) - [i263]Guan-Ting Lin, David Cheng-Han Chiang, Hung-yi Lee:
Advancing Large Language Models to Capture Varied Speaking Styles and Respond Properly in Spoken Conversations. CoRR abs/2402.12786 (2024) - [i262]Haibin Wu, Huang-Cheng Chou, Kai-Wei Chang, Lucas Goncalves, Jiawei Du, Jyh-Shing Roger Jang, Chi-Chun Lee, Hung-Yi Lee:
EMO-SUPERB: An In-depth Look at Speech Emotion Recognition. CoRR abs/2402.13018 (2024) - [i261]Haibin Wu, Ho-Lam Chung, Yi-Cheng Lin, Yuan-Kuei Wu, Xuanjun Chen, Yu-Chi Pai, Hsiu-Hsuan Wang, Kai-Wei Chang, Alexander H. Liu, Hung-yi Lee:
Codec-SUPERB: An In-Depth Analysis of Sound Codec Models. CoRR abs/2402.13071 (2024) - [i260]Haibin Wu, Xuanjun Chen, Yi-Cheng Lin, Kai-Wei Chang, Ho-Lam Chung, Alexander H. Liu, Hung-yi Lee:
Towards audio language modeling - an overview. CoRR abs/2402.13236 (2024) - [i259]Shu-Wen Yang, Heng-Jui Chang, Zili Huang, Andy T. Liu, Cheng-I Lai, Haibin Wu, Jiatong Shi, Xuankai Chang, Hsiang-Sheng Tsai, Wen-Chin Huang, Tzu-hsun Feng, Po-Han Chi, Yist Y. Lin, Yung-Sung Chuang, Tzu-Hsien Huang, Wei-Cheng Tseng, Kushal Lakhotia, Shang-Wen Li, Abdelrahman Mohamed, Shinji Watanabe, Hung-yi Lee:
A Large-Scale Evaluation of Speech Foundation Models. CoRR abs/2404.09385 (2024) - [i258]Li-Chun Lu, Shou-Jen Chen, Tsung-Min Pai, Chan-Hung Yu, Hung-yi Lee, Shao-Hua Sun:
LLM Discussion: Enhancing the Creativity of Large Language Models via Discussion Framework and Role-Play. CoRR abs/2405.06373 (2024) - [i257]Kuang-Ming Chen, Hung-yi Lee:
InstructionCP: A fast approach to transfer Large Language Models into target language. CoRR abs/2405.20175 (2024) - [i256]Hsuan Su, Hua Farn, Fan-Yun Sun, Shang-Tse Chen, Hung-yi Lee:
Task Arithmetic can Mitigate Synthetic-to-Real Gap in Automatic Speech Recognition. CoRR abs/2406.02925 (2024) - [i255]Fabian Ritter Gutierrez, Kuan-Po Huang, Jeremy H. M. Wong, Dianwen Ng, Hung-yi Lee, Nancy F. Chen, Eng Siong Chng:
Dataset-Distillation Generative Model for Speech Emotion Recognition. CoRR abs/2406.02963 (2024) - [i254]Xuanjun Chen, Jiawei Du, Haibin Wu, Jyh-Shing Roger Jang, Hung-yi Lee:
Neural Codec-based Adversarial Sample Detection for Speaker Verification. CoRR abs/2406.04582 (2024) - [i253]Yi-Cheng Lin, Tzu-Quan Lin, Hsi-Che Lin, Andy T. Liu, Hung-yi Lee:
On the social bias of speech self-supervised models. CoRR abs/2406.04997 (2024) - [i252]Tzu-Quan Lin, Hung-yi Lee, Hao Tang:
DAISY: Data Adaptive Self-Supervised Early Exit for Speech Representation Models. CoRR abs/2406.05464 (2024) - [i251]Chih-Kai Yang, Kuan-Po Huang, Hung-yi Lee:
Do Prompts Really Prompt? Exploring the Prompt Understanding Capability of Whisper. CoRR abs/2406.05806 (2024) - [i250]Haibin Wu, Yuan Tseng, Hung-yi Lee:
CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems. CoRR abs/2406.07237 (2024) - [i249]Chun-Yi Kuan, Wei-Ping Huang, Hung-yi Lee:
Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models. CoRR abs/2406.08402 (2024) - [i248]Jiatong Shi, Shih-Heng Wang, William Chen, Martijn Bartelds, Vanya Bannihatti Kumar, Jinchuan Tian, Xuankai Chang, Dan Jurafsky, Karen Livescu, Hung-yi Lee, Shinji Watanabe:
ML-SUPERB 2.0: Benchmarking Multilingual Speech Models Across Modeling Constraints, Languages, and Datasets. CoRR abs/2406.08641 (2024) - [i247]Cheng-Kuang Wu, Zhi Rui Tam, Chieh-Yen Lin, Yun-Nung Chen, Hung-yi Lee:
StreamBench: Towards Benchmarking Continuous Improvement of Language Agents. CoRR abs/2406.08747 (2024) - [i246]Siddhant Arora, Ankita Pasad, Chung-Ming Chien, Jionghao Han, Roshan S. Sharma, Jee-weon Jung, Hira Dhamyal, William Chen, Suwon Shon, Hung-yi Lee, Karen Livescu, Shinji Watanabe:
On the Evaluation of Speech Foundation Models for Spoken Language Understanding. CoRR abs/2406.10083 (2024) - [i245]Hung-Ting Su, Chun-Tong Chao, Ya-Ching Hsu, Xudong Lin, Yulei Niu, Hung-Yi Lee, Winston H. Hsu:
Investigating Video Reasoning Capability of Large Language Models with Tropes in Movies. CoRR abs/2406.10923 (2024) - [i244]Guan-Ting Lin, Wei-Ping Huang, Hung-yi Lee:
Continual Test-time Adaptation for End-to-end Speech Recognition on Noisy Speech. CoRR abs/2406.11064 (2024) - [i243]Guan-Ting Lin, Hung-yi Lee:
Can LLMs Understand the Implication of Emphasized Sentences in Dialogue? CoRR abs/2406.11065 (2024) - [i242]Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu, He Huang, Boris Ginsburg, Yu-Chiang Frank Wang, Hung-yi Lee:
DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignment. CoRR abs/2406.18871 (2024) - [i241]Tzu-Han Lin, Chen-An Li, Hung-yi Lee, Yun-Nung Chen:
DogeRM: Equipping Reward Models with Domain Knowledge through Model Merging. CoRR abs/2407.01470 (2024) - [i240]Yu-Kuan Fu, Cheng-Kuang Lee, Hsiu-Hsuan Wang, Hung-yi Lee:
Investigating the Effects of Large-Scale Pseudo-Stereo Data and Different Speech Foundation Model on Dialogue Generative Spoken Language Model. CoRR abs/2407.01911 (2024) - [i239]Cheng-Han Chiang, Wei-Chih Chen, Chun-Yi Kuan, Chienchou Yang, Hung-yi Lee:
Large Language Model as an Assignment Evaluator: Insights, Feedback, and Challenges in a 1000+ Student Course. CoRR abs/2407.05216 (2024) - [i238]Yi-Cheng Lin, Tzu-Quan Lin, Chih-Kai Yang, Ke-Han Lu, Wei-Chih Chen, Chun-Yi Kuan, Hung-yi Lee:
Listen and Speak Fairly: A Study on Semantic Gender Bias in Speech Integrated Large Language Models. CoRR abs/2407.06957 (2024) - [i237]Chun-Yi Kuan, Chih-Kai Yang, Wei-Ping Huang, Ke-Han Lu, Hung-yi Lee:
Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generation. CoRR abs/2407.09886 (2024) - [i236]Liang-Hsuan Tseng, Zih-Ching Chen, Wei-Shun Chang, Cheng-Kuang Lee, Tsung-Ren Huang, Hung-yi Lee:
Leave No Knowledge Behind During Knowledge Distillation: Towards Practical and Effective Knowledge Distillation for Code-Switching ASR Using Realistic Data. CoRR abs/2407.10603 (2024) - [i235]Cheng-Kuang Wu, Zhi Rui Tam, Chao-Chung Wu, Chieh-Yen Lin, Hung-yi Lee, Yun-Nung Chen:
I Need Help! Evaluating LLM's Ability to Ask for Users' Support: A Case Study on Text-to-SQL Generation. CoRR abs/2407.14767 (2024) - [i234]Wenze Ren, Yi-Cheng Lin, Huang-Cheng Chou, Haibin Wu, Yi-Chiao Wu, Chi-Chun Lee, Hung-yi Lee, Yu Tsao:
EMO-Codec: An In-Depth Look at Emotion Preservation capacity of Legacy and Neural Codec Models With Subjective and Objective Evaluations. CoRR abs/2407.15458 (2024) - [i233]Zhi Rui Tam, Cheng-Kuang Wu, Yi-Lin Tsai, Chieh-Yen Lin, Hung-yi Lee, Yun-Nung Chen:
Let Me Speak Freely? A Study on the Impact of Format Restrictions on Performance of Large Language Models. CoRR abs/2408.02442 (2024) - [i232]Shachi H. Kumar, Saurav Sahay, Sahisnu Mazumder, Eda Okur, Ramesh Manuvinakurike, Nicole Beckage, Hsuan Su, Hung-yi Lee, Lama Nachman:
Decoding Biases: Automated Methods and LLM Judges for Gender Bias Detection in Language Models. CoRR abs/2408.03907 (2024) - [i231]Yi-Cheng Lin, Wei-Chih Chen, Hung-yi Lee:
Spoken Stereoset: On Evaluating Social Bias Toward Speaker in Speech Large Language Models. CoRR abs/2408.07665 (2024) - [i230]Kai-Wei Chang, Haibin Wu, Yu-Kai Wang, Yuan-Kuei Wu, Hua Shen, Wei-Cheng Tseng, Iu-thing Kang, Shang-Wen Li, Hung-yi Lee:
SpeechPrompt: Prompting Speech Language Models for Speech Processing Tasks. CoRR abs/2408.13040 (2024) - [i229]Chien-yu Huang, Min-Han Shih, Ke-Han Lu, Chi-Yuan Hsiao, Hung-yi Lee:
SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning. CoRR abs/2408.13891 (2024) - [i228]Juncheng Xie, Shensian Syu, Hung-yi Lee:
Non-instructional Fine-tuning: Enabling Instruction-Following Capabilities in Pre-trained Language Models without Instruction-Following Data. CoRR abs/2409.00096 (2024) - [i227]Tzu-Quan Lin, Guan-Ting Lin, Hung-yi Lee, Hao Tang:
Property Neurons in Self-Supervised Speech Transformers. CoRR abs/2409.05910 (2024) - [i226]Jiawei Du, I-Ming Lin, I-Hsiang Chiu, Xuanjun Chen, Haibin Wu, Wenze Ren, Yu Tsao, Hung-yi Lee, Jyh-Shing Roger Jang:
DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Dataset. CoRR abs/2409.08731 (2024) - [i225]Ming-Hao Hsu, Kuan Po Huang, Hung-yi Lee:
Meta-Whisper: Speech-Based Meta-ICL for ASR on Low-Resource Languages. CoRR abs/2409.10429 (2024) - [i224]Hsi-Che Lin, Yi-Cheng Lin, Huang-Cheng Chou, Hung-yi Lee:
Improving Speech Emotion Recognition in Under-Resourced Languages via Speech-to-Speech Translation with Bootstrapping Data Selection. CoRR abs/2409.10985 (2024) - [i223]Haibin Wu, Xuanjun Chen, Yi-Cheng Lin, Kai-Wei Chang, Jiawei Du, Ke-Han Lu, Alexander H. Liu, Ho-Lam Chung, Yuan-Kuei Wu, Dongchao Yang, Songxiang Liu, Yi-Chiao Wu, Xu Tan, James R. Glass, Shinji Watanabe, Hung-yi Lee:
Codec-SUPERB @ SLT 2024: A lightweight benchmark for neural audio codec models. CoRR abs/2409.14085 (2024) - [i222]Hung-Ting Su, Ya-Ching Hsu, Xudong Lin, Xiang Qian Shi, Yulei Niu, Han-Yuan Hsu, Hung-yi Lee, Winston H. Hsu:
Unveiling Narrative Reasoning Limits of Large Language Models with Trope in Movie Synopses. CoRR abs/2409.14324 (2024) - [i221]Andy T. Liu, Yi-Cheng Lin, Haibin Wu, Stefan Winkler, Hung-yi Lee:
Efficient Training of Self-Supervised Speech Foundation Models on a Compute Budget. CoRR abs/2409.16295 (2024) - [i220]Ke-Han Lu, Zhehuai Chen, Szu-Wei Fu, Chao-Han Huck Yang, Jagadeesh Balam, Boris Ginsburg, Yu-Chiang Frank Wang, Hung-yi Lee:
Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data. CoRR abs/2409.20007 (2024) - [i219]Yun-Yen Chuang, Hung-Min Hsu, Kevin Lin, Chen-Sheng Gu, Ling Zhen Li, Ray-I Chang, Hung-yi Lee:
Meta-DiffuB: A Contextualized Sequence-to-Sequence Text Diffusion Model with Meta-Exploration. CoRR abs/2410.13201 (2024) - [i218]Chun-Yi Kuan, Hung-yi Lee:
Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning. CoRR abs/2410.16130 (2024) - [i217]Guan-Ting Lin, Prashanth Gurunath Shivakumar, Aditya Gourav, Yile Gu, Ankur Gandhe, Hung-yi Lee, Ivan Bulyko:
Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback. CoRR abs/2411.01834 (2024) - 2023
- [j24]Po-Chun Hsu, Da-Rong Liu, Andy T. Liu, Hung-yi Lee:
Parallel Synthesis for Autoregressive Speech Generation. IEEE ACM Trans. Audio Speech Lang. Process. 31: 3095-3111 (2023) - [j23]Yun-Yen Chuang, Hung-Min Hsu, Kevin Lin, Ray-I Chang, Hung-Yi Lee:
MetaEx-GAN: Meta Exploration to Improve Natural Language Generation via Generative Adversarial Networks. IEEE ACM Trans. Audio Speech Lang. Process. 31: 3968-3980 (2023) - [c195]David Cheng-Han Chiang, Hung-yi Lee:
Are Synonym Substitution Attacks Really Synonym Substitution Attacks? ACL (Findings) 2023: 1853-1878 - [c194]Suwon Shon, Siddhant Arora, Chyi-Jiunn Lin, Ankita Pasad, Felix Wu, Roshan S. Sharma, Wei-Lun Wu, Hung-yi Lee, Karen Livescu, Shinji Watanabe:
SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks. ACL (1) 2023: 8906-8937 - [c193]Derek Xu, Shuyan Dong, Changhan Wang, Suyoun Kim, Zhaojiang Lin, Bing Liu, Akshat Shrivastava, Shang-Wen Li, Liang-Hsuan Tseng, Guan-Ting Lin, Alexei Baevski, Hung-yi Lee, Yizhou Sun, Wei Wang:
Introducing Semantics into Speech Encoders. ACL (1) 2023: 11413-11429 - [c192]David Cheng-Han Chiang, Hung-yi Lee:
Can Large Language Models Be an Alternative to Human Evaluations? ACL (1) 2023: 15607-15631 - [c191]Kai-Wei Chang, Ming-Hsin Chen, Yun-Ping Lin, Jing Neng Hsu, Paul Kuo-Ming Huang, Chien-Yu Huang, Shang-Wen Li, Hung-Yi Lee:
Prompting and Adapter Tuning For Self-Supervised Encoder-Decoder Speech Model. ASRU 2023: 1-8 - [c190]Wei-Ping Huang, Sung-Feng Huang, Hung-Yi Lee:
Maximizing Data Efficiency for Cross-Lingual TTS Adaptation by Self-Supervised Representation Mixing and Embedding Initialization. ASRU 2023: 1-8 - [c189]Chun-Yi Kuan, Chen-An Li, Tsu-Yuan Hsu, Tse-Yang Lin, Ho-Lam Chung, Kai-Wei Chang, Shuo-Yiin Chang, Hung-Yi Lee:
Towards General-Purpose Text-Instruction-Guided Voice Conversion. ASRU 2023: 1-8 - [c188]Tzu-Quan Lin, Hung-Yi Lee, Hao Tang:
MelHuBERT: A Simplified Hubert on Mel Spectrograms. ASRU 2023: 1-8 - [c187]Jiatong Shi, William Chen, Dan Berrebbi, Hsiu-Hsuan Wang, Wei-Ping Huang, En-Pei Hu, Ho-Lam Chuang, Xuankai Chang, Yuxun Tang, Shang-Wen Li, Abdelrahman Mohamed, Hung-Yi Lee, Shinji Watanabe:
Findings of the 2023 ML-Superb Challenge: Pre-Training And Evaluation Over More Languages And Beyond. ASRU 2023: 1-8 - [c186]Yu-Hsiang Wang, Huang-Yu Chen, Kai-Wei Chang, Winston H. Hsu, Hung-Yi Lee:
Minisuperb: Lightweight Benchmark for Self-Supervised Speech Models. ASRU 2023: 1-8 - [c185]Jun-You Wang, Hung-Yi Lee, Jyh-Shing Roger Jang, Li Su:
Zero-Shot Singing Voice Synthesis from Musical Score. ASRU 2023: 1-8 - [c184]Haibin Wu, Jiawen Kang, Lingwei Meng, Helen Meng, Hung-yi Lee:
The Defender's Perspective on Automatic Speaker Verification: An Overview. DADA@IJCAI 2023: 6-11 - [c183]David Cheng-Han Chiang, Hung-yi Lee:
A Closer Look into Using Large Language Models for Automatic Evaluation. EMNLP (Findings) 2023: 8928-8942 - [c182]Layne Berry, Yi-Jen Shih, Hsuan-Fu Wang, Heng-Jui Chang, Hung-Yi Lee, David Harwath:
M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval. ICASSP 2023: 1-5 - [c181]Hsuan-Jui Chen, Yen Meng, Hung-yi Lee:
Once-for-All Sequence Compression for Self-Supervised Speech Models. ICASSP 2023: 1-5 - [c180]Zih-Ching Chen, Yu-Shun Sung, Hung-Yi Lee:
Chapter: Exploiting Convolutional Neural Network Adapters for Self-Supervised Speech Models. ICASSP Workshops 2023: 1-5 - [c179]Dongji Gao, Jiatong Shi, Shun-Po Chuang, Leibny Paola García, Hung-Yi Lee, Shinji Watanabe, Sanjeev Khudanpur:
Euro: Espnet Unsupervised ASR Open-Source Toolkit. ICASSP 2023: 1-5 - [c178]Chan-Jan Hsu, Ho-Lam Chung, Hung-Yi Lee, Yu Tsao:
T5lephone: Bridging Speech and Text Self-Supervised Models for Spoken Language Understanding Via Phoneme Level T5. ICASSP 2023: 1-5 - [c177]Sung-Feng Huang, Chia-Ping Chen, Zhi-Sheng Chen, Yu-Pao Tsai, Hung-Yi Lee:
Personalized Lightweight Text-to-Speech: Voice Cloning with Adaptive Structured Pruning. ICASSP 2023: 1-5 - [c176]Kuan-Po Huang, Tzu-hsun Feng, Yu-Kuan Fu, Tsu-Yuan Hsu, Po-Chieh Yen, Wei-Cheng Tseng, Kai-Wei Chang, Hung-Yi Lee:
Ensemble Knowledge Distillation of Self-Supervised Speech Models. ICASSP 2023: 1-5 - [c175]Jiatong Shi, Chan-Jan Hsu, Ho-Lam Chung, Dongji Gao, Paola García, Shinji Watanabe, Ann Lee, Hung-Yi Lee:
Bridging Speech and Textual Pre-Trained Models With Unsupervised ASR. ICASSP 2023: 1-5 - [c174]Yuan Tseng, Cheng-I Jeff Lai, Hung-Yi Lee:
Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences. ICASSP 2023: 1-5 - [c173]Guan-Ting Liu, En-Pei Hu, Pu-Jen Cheng, Hung-Yi Lee, Shao-Hua Sun:
Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs. ICML 2023: 21672-21697 - [c172]Zih-Ching Chen, Chao-Han Huck Yang, Bo Li, Yu Zhang, Nanxin Chen, Shuo-Yiin Chang, Rohit Prabhavalkar, Hung-yi Lee, Tara N. Sainath:
How to Estimate Model Transferability of Pre-Trained Speech Models? INTERSPEECH 2023: 456-460 - [c171]Jiatong Shi, Dan Berrebbi, William Chen, En-Pei Hu, Wei-Ping Huang, Ho-Lam Chung, Xuankai Chang, Shang-Wen Li, Abdelrahman Mohamed, Hung-yi Lee, Shinji Watanabe:
ML-SUPERB: Multilingual Speech Universal PERformance Benchmark. INTERSPEECH 2023: 884-888 - [c170]Guan-Wei Wu, Guan-Ting Lin, Shang-Wen Li, Hung-yi Lee:
Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Target. INTERSPEECH 2023: 1503-1507 - [c169]Cheng-Han Chiang, Wei-Ping Huang, Hung-yi Lee:
Why We Should Report the Details in Subjective Evaluation of TTS More Rigorously. INTERSPEECH 2023: 5551-5555 - [c168]David Cheng-Han Chiang, Hung-yi Lee, Yung-Sung Chuang, James R. Glass:
Revealing the Blind Spot of Sentence Encoder Evaluation by HEROS. RepL4NLP@ACL 2023: 289-302 - [e2]C. Maria Keet, Hung-Yi Lee, Sina Zarrieß:
Proceedings of the 16th International Natural Language Generation Conference, INLG 2023, Prague, Czechia, September 11 - 15, 2023. Association for Computational Linguistics 2023, ISBN 979-8-89176-001-1 [contents] - [i216]Guan-Ting Liu, En-Pei Hu, Pu-Jen Cheng, Hung-Yi Lee, Shao-Hua Sun:
Hierarchical Programmatic Reinforcement Learning via Learning to Compose Programs. CoRR abs/2301.12950 (2023) - [i215]Hsuan Su, Shachi H. Kumar, Sahisnu Mazumder, Wenda Chen, Ramesh Manuvinakurike, Eda Okur, Saurav Sahay, Lama Nachman, Shang-Tse Chen, Hung-yi Lee:
Position Matters! Empirical Study of Order Effect in Knowledge-grounded Dialogue. CoRR abs/2302.05888 (2023) - [i214]Kuan-Po Huang, Tzu-hsun Feng, Yu-Kuan Fu, Tsu-Yuan Hsu, Po-Chieh Yen, Wei-Cheng Tseng, Kai-Wei Chang, Hung-yi Lee:
Ensemble knowledge distillation of self-supervised speech models. CoRR abs/2302.12757 (2023) - [i213]Kai-Wei Chang, Yu-Kai Wang, Hua Shen, Iu-thing Kang, Wei-Cheng Tseng, Shang-Wen Li, Hung-yi Lee:
SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks. CoRR abs/2303.00733 (2023) - [i212]Yuan Tseng, Cheng-I Lai, Hung-yi Lee:
Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken Sentences. CoRR abs/2303.08809 (2023) - [i211]Sung-Feng Huang, Chia-Ping Chen, Zhi-Sheng Chen, Yu-Pao Tsai, Hung-yi Lee:
Personalized Lightweight Text-to-Speech: Voice Cloning with Adaptive Structured Pruning. CoRR abs/2303.11816 (2023) - [i210]David Cheng-Han Chiang, Hung-yi Lee:
Can Large Language Models Be an Alternative to Human Evaluations? CoRR abs/2305.01937 (2023) - [i209]Yu-Kuan Fu, Liang-Hsuan Tseng, Jiatong Shi, Chen-An Li, Tsu-Yuan Hsu, Shinji Watanabe, Hung-Yi Lee:
Improving Cascaded Unsupervised Speech Translation with Denoising Back-translation. CoRR abs/2305.07455 (2023) - [i208]Jiatong Shi, Dan Berrebbi, William Chen, Ho-Lam Chung, En-Pei Hu, Wei-Ping Huang, Xuankai Chang, Shang-Wen Li, Abdelrahman Mohamed, Hung-yi Lee, Shinji Watanabe:
ML-SUPERB: Multilingual Speech Universal PERformance Benchmark. CoRR abs/2305.10615 (2023) - [i207]Haibin Wu, Jiawen Kang, Lingwei Meng, Helen Meng, Hung-yi Lee:
The defender's perspective on automatic speaker verification: An overview. CoRR abs/2305.12804 (2023) - [i206]Guan-Wei Wu, Guan-Ting Lin, Shang-Wen Li, Hung-yi Lee:
Improving Textless Spoken Language Understanding with Discrete Units as Intermediate Target. CoRR abs/2305.18096 (2023) - [i205]Yu-Hsiang Wang, Huang-Yu Chen, Kai-Wei Chang, Winston H. Hsu, Hung-yi Lee:
MiniSUPERB: Lightweight Benchmark for Self-supervised Speech Models. CoRR abs/2305.19011 (2023) - [i204]Zih-Ching Chen, Chao-Han Huck Yang, Bo Li, Yu Zhang, Nanxin Chen, Shuo-Yiin Chang, Rohit Prabhavalkar, Hung-yi Lee, Tara N. Sainath:
How to Estimate Model Transferability of Pre-Trained Speech Models? CoRR abs/2306.01015 (2023) - [i203]Haibin Wu, Kai-Wei Chang, Yuan-Kuei Wu, Hung-yi Lee:
SpeechGen: Unlocking the Generative Power of Speech Language Models with Prompts. CoRR abs/2306.02207 (2023) - [i202]David Cheng-Han Chiang, Yung-Sung Chuang, James R. Glass, Hung-yi Lee:
Revealing the Blind Spot of Sentence Encoder Evaluation by HEROS. CoRR abs/2306.05083 (2023) - [i201]Shen-sian Syu, Juncheng Xie, Hung-yi Lee:
Improving Non-autoregressive Translation Quality with Pretrained Language Model, Embedding Distillation and Upsampling Strategy for CTC. CoRR abs/2306.06345 (2023) - [i200]Chien-yu Huang, Ke-Han Lu, Shih-Heng Wang, Chi-Yuan Hsiao, Chun-Yi Kuan, Haibin Wu, Siddhant Arora, Kai-Wei Chang, Jiatong Shi, Yifan Peng, Roshan S. Sharma, Shinji Watanabe, Bhiksha Ramakrishnan, Shady Shehata, Hung-yi Lee:
Dynamic-SUPERB: Towards A Dynamic, Collaborative, and Comprehensive Instruction-Tuning Benchmark for Speech. CoRR abs/2309.09510 (2023) - [i199]Yuan Tseng, Layne Berry, Yi-Ting Chen, I-Hsiang Chiu, Hsuan-Hao Lin, Max Liu, Puyuan Peng, Yi-Jen Shih, Hung-Yu Wang, Haibin Wu, Po-Yao Huang, Chun-Mao Lai, Shang-Wen Li, David Harwath, Yu Tsao, Shinji Watanabe, Abdelrahman Mohamed, Chi-Luen Feng, Hung-yi Lee:
AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models. CoRR abs/2309.10787 (2023) - [i198]Chun-Yi Kuan, Chen-An Li, Tsu-Yuan Hsu, Tse-Yang Lin, Ho-Lam Chung, Kai-Wei Chang, Shuo-Yiin Chang, Hung-yi Lee:
Towards General-Purpose Text-Instruction-Guided Voice Conversion. CoRR abs/2309.14324 (2023) - [i197]Dennis Y. Menn, Tzu-hsun Feng, Sriram Vishwanath, Hung-yi Lee:
Investigating Human-Identifiable Features Hidden in Adversarial Perturbations. CoRR abs/2309.16878 (2023) - [i196]Po-Chun Hsu, Ali Elkahky, Wei-Ning Hsu, Yossi Adi, Tu Anh Nguyen, Jade Copet, Emmanuel Dupoux, Hung-yi Lee, Abdelrahman Mohamed:
Low-Resource Self-Supervised Learning with SSL-Enhanced TTS. CoRR abs/2309.17020 (2023) - [i195]Kai-Wei Chang, Ming-Hsin Chen, Yun-Ping Lin, Jing Neng Hsu, Paul Kuo-Ming Huang, Chien-Yu Huang, Shang-Wen Li, Hung-yi Lee:
Prompting and Adapter Tuning for Self-supervised Encoder-Decoder Speech Model. CoRR abs/2310.02971 (2023) - [i194]Kuan-Po Huang, Chih-Kai Yang, Yu-Kuan Fu, Ewan Dunbar, Hung-yi Lee:
Zero Resource Code-switched Speech Benchmark Using Speech Utterance Pairs For Multiple Spoken Languages. CoRR abs/2310.03018 (2023) - [i193]Shih-Cheng Huang, Pin-Zu Li, Yu-Chi Hsu, Kuang-Ming Chen, Yu-Tung Lin, Shih-Kai Hsiao, Richard Tzong-Han Tsai, Hung-yi Lee:
Chat Vector: A Simple Approach to Equip LLMs With New Language Chat Capabilities. CoRR abs/2310.04799 (2023) - [i192]Jiatong Shi, William Chen, Dan Berrebbi, Hsiu-Hsuan Wang, Wei-Ping Huang, En-Pei Hu, Ho-Lam Chung, Xuankai Chang, Yuxun Tang, Shang-Wen Li, Abdelrahman Mohamed, Hung-yi Lee, Shinji Watanabe:
Findings of the 2023 ML-SUPERB Challenge: Pre-Training and Evaluation over More Languages and Beyond. CoRR abs/2310.05513 (2023) - [i191]David Cheng-Han Chiang, Hung-yi Lee:
A Closer Look into Automatic Evaluation Using Large Language Models. CoRR abs/2310.05657 (2023) - [i190]Hsuan Su, Cheng-Chu Cheng, Hua Farn, Shachi H. Kumar, Saurav Sahay, Shang-Tse Chen, Hung-yi Lee:
Learning from Red Teaming: Gender Bias Provocation and Mitigation in Large Language Models. CoRR abs/2310.11079 (2023) - [i189]Ming-Hao Hsu, Kai-Wei Chang, Shang-Wen Li, Hung-yi Lee:
An Exploration of In-Context Learning for Speech Language Model. CoRR abs/2310.12477 (2023) - [i188]Hsuan Su, Rebecca Qian, Chinnadhurai Sankar, Shahin Shayandeh, Shang-Tse Chen, Hung-yi Lee, Daniel M. Bikel:
Step by Step to Fairness: Attributing Societal Bias in Task-oriented Dialogue Systems. CoRR abs/2311.06513 (2023) - [i187]Haibin Wu, Heng-Cheng Kuo, Yu Tsao, Hung-yi Lee:
Scalable Ensemble-based Detection Method against Adversarial Attacks for speaker verification. CoRR abs/2312.08622 (2023) - [i186]Min-Han Shih, Ho-Lam Chung, Yu-Chi Pai, Ming-Hao Hsu, Guan-Ting Lin, Shang-Wen Li, Hung-Yi Lee:
GSQA: An End-to-End Model for Generative Spoken Question Answering. CoRR abs/2312.09781 (2023) - [i185]Fabian Ritter Gutierrez, Kuan-Po Huang, Dianwen Ng, Jeremy Heng Meng Wong, Hung-yi Lee, Eng Siong Chng, Nancy F. Chen:
Noise robust distillation of self-supervised speech models via correlation metrics. CoRR abs/2312.12153 (2023) - [i184]Guan-Ting Lin, Prashanth Gurunath Shivakumar, Ankur Gandhe, Chao-Han Huck Yang, Yile Gu, Shalini Ghosh, Andreas Stolcke, Hung-yi Lee, Ivan Bulyko:
Paralinguistics-Enhanced Large Language Modeling of Spoken Dialogue. CoRR abs/2312.15316 (2023) - 2022
- [j22]Hung-Yi Lee, Shinji Watanabe, Karen Livescu, Abdelrahman Mohamed, Tara N. Sainath:
Editorial Editorial of Special Issue on Self-Supervised Learning for Speech and Audio Processing. IEEE J. Sel. Top. Signal Process. 16(6): 1174-1178 (2022) - [j21]Abdelrahman Mohamed, Hung-yi Lee, Lasse Borgholt, Jakob D. Havtorn, Joakim Edin, Christian Igel, Katrin Kirchhoff, Shang-Wen Li, Karen Livescu, Lars Maaløe, Tara N. Sainath, Shinji Watanabe:
Self-Supervised Speech Representation Learning: A Review. IEEE J. Sel. Top. Signal Process. 16(6): 1179-1210 (2022) - [j20]Haibin Wu, Xu Li, Andy T. Liu, Zhiyong Wu, Helen Meng, Hung-Yi Lee:
Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning. IEEE ACM Trans. Audio Speech Lang. Process. 30: 202-217 (2022) - [j19]Da-Rong Liu, Po-Chun Hsu, Yi-Chen Chen, Sung-Feng Huang, Shun-Po Chuang, Da-Yi Wu, Hung-yi Lee:
Learning Phone Recognition From Unpaired Audio and Phone Sequences Based on Generative Adversarial Network. IEEE ACM Trans. Audio Speech Lang. Process. 30: 230-243 (2022) - [j18]Sung-Feng Huang, Chyi-Jiunn Lin, Da-Rong Liu, Yi-Chen Chen, Hung-yi Lee:
Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech. IEEE ACM Trans. Audio Speech Lang. Process. 30: 1558-1571 (2022) - [j17]Yi-Long Liou, Jui-Yang Hsu, Chen-Sheng Chen, Alexander H. Liu, Hung-Yi Lee, Tsung-Te Liu:
A Fully Integrated 1.7mW Attention-Based Automatic Speech Recognition Processor. IEEE Trans. Circuits Syst. II Express Briefs 69(10): 4178-4182 (2022) - [c167]David Cheng-Han Chiang, Hung-Yi Lee:
On the Transferability of Pre-trained Language Models: A Study from Artificial Datasets. AAAI 2022: 10518-10525 - [c166]Chan-Jan Hsu, Hung-yi Lee, Yu Tsao:
XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding. ACL (2) 2022: 479-489 - [c165]Hsiang-Sheng Tsai, Heng-Jui Chang, Wen-Chin Huang, Zili Huang, Kushal Lakhotia, Shu-Wen Yang, Shuyan Dong, Andy T. Liu, Cheng-I Lai, Jiatong Shi, Xuankai Chang, Phil Hall, Hsuan-Jui Chen, Shang-Wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-yi Lee:
SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities. ACL (1) 2022: 8479-8492 - [c164]Haibin Wu, Po-Chun Hsu, Ji Gao, Shanshan Zhang, Shen Huang, Jian Kang, Zhiyong Wu, Helen Meng, Hung-Yi Lee:
Adversarial Sample Detection for Speaker Verification by Neural Vocoders. ICASSP 2022: 236-240 - [c163]Haibin Wu, Bo Zheng, Xu Li, Xixin Wu, Hung-Yi Lee, Helen Meng:
Characterizing the Adversarial Vulnerability of Speech self-Supervised Learning. ICASSP 2022: 3164-3168 - [c162]Yen Meng, Yi-Hui Chou, Andy T. Liu, Hung-yi Lee:
Don't Speak Too Fast: The Impact of Data Bias on Self-Supervised Speech Models. ICASSP 2022: 3258-3262 - [c161]Wen-Chin Huang, Shu-Wen Yang, Tomoki Hayashi, Hung-Yi Lee, Shinji Watanabe, Tomoki Toda:
S3PRL-VC: Open-Source Voice Conversion Framework with Self-Supervised Speech Representations. ICASSP 2022: 6552-6556 - [c160]Chien-yu Huang, Kai-Wei Chang, Hung-Yi Lee:
Toward Degradation-Robust Voice Conversion. ICASSP 2022: 6777-6781 - [c159]Heng-Jui Chang, Shu-Wen Yang, Hung-yi Lee:
Distilhubert: Speech Representation Learning by Layer-Wise Distillation of Hidden-Unit Bert. ICASSP 2022: 7087-7091 - [c158]Guan-Ting Lin, Chan-Jan Hsu, Da-Rong Liu, Hung-Yi Lee, Yu Tsao:
Analyzing The Robustness of Unsupervised Speech Recognition. ICASSP 2022: 8202-8206 - [c157]Haibin Wu, Heng-Cheng Kuo, Naijun Zheng, Kuo-Hsuan Hung, Hung-Yi Lee, Yu Tsao, Hsin-Min Wang, Helen Meng:
Partially Fake Audio Detection by Self-Attention-Based Fake Span Discovery. ICASSP 2022: 9236-9240 - [c156]Yang Zhang, Zhiqiang Lv, Haibin Wu, Shanshan Zhang, Pengfei Hu, Zhiyong Wu, Hung-yi Lee, Helen Meng:
MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification. INTERSPEECH 2022: 306-310 - [c155]Kuan-Po Huang, Yu-Kuan Fu, Yu Zhang, Hung-yi Lee:
Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation. INTERSPEECH 2022: 2193-2197 - [c154]Guan-Ting Lin, Shang-Wen Li, Hung-yi Lee:
Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition. INTERSPEECH 2022: 2198-2202 - [c153]Haibin Wu, Lingwei Meng, Jiawen Kang, Jinchao Li, Xu Li, Xixin Wu, Hung-yi Lee, Helen Meng:
Spoofing-Aware Speaker Verification by Multi-Level Fusion. INTERSPEECH 2022: 4357-4361 - [c152]Wei-Cheng Tseng, Wei-Tsung Kao, Hung-yi Lee:
DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scores. INTERSPEECH 2022: 4541-4545 - [c151]Wei-Ping Huang, Po-Chun Chen, Sung-Feng Huang, Hung-yi Lee:
Few Shot Cross-Lingual TTS Using Transferable Phoneme Embedding. INTERSPEECH 2022: 4566-4570 - [c150]Kai-Wei Chang, Wei-Cheng Tseng, Shang-Wen Li, Hung-yi Lee:
An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks. INTERSPEECH 2022: 5005-5009 - [c149]Wei-Cheng Tseng, Wei-Tsung Kao, Hung-yi Lee:
Membership Inference Attacks Against Self-supervised Speech Models. INTERSPEECH 2022: 5040-5044 - [c148]Guan-Ting Lin, Yung-Sung Chuang, Ho-Lam Chung, Shu-Wen Yang, Hsuan-Jui Chen, Shuyan Annie Dong, Shang-Wen Li, Abdelrahman Mohamed, Hung-yi Lee, Lin-Shan Lee:
DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering. INTERSPEECH 2022: 5165-5169 - [c147]Chih-Chiang Chang, Hung-yi Lee:
Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation. INTERSPEECH 2022: 5175-5179 - [c146]Chih-Chiang Chang, Shun-Po Chuang, Hung-yi Lee:
Anticipation-Free Training for Simultaneous Machine Translation. IWSLT@ACL 2022: 43-61 - [c145]Hung-yi Lee, Shang-Wen Li, Thang Vu:
Meta Learning for Natural Language Processing: A Survey. NAACL-HLT 2022: 666-684 - [c144]Chin-Lun Fu, Zih-Ching Chen, Yun-Ru Lee, Hung-yi Lee:
AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks. NAACL-HLT (Findings) 2022: 2608-2621 - [c143]Haibin Wu, Jiawen Kang, Lingwei Meng, Yang Zhang, Xixin Wu, Zhiyong Wu, Hung-yi Lee, Helen Meng:
Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion. Odyssey 2022: 92-99 - [c142]Wei-Tsung Kao, Yuan-Kuei Wu, Chia-Ping Chen, Zhi-Sheng Chen, Yu-Pao Tsai, Hung-Yi Lee:
On the Efficiency of Integrating Self-Supervised Learning and Meta-Learning for User-Defined Few-Shot Keyword Spotting. SLT 2022: 414-421 - [c141]Xuanjun Chen, Haibin Wu, Helen Meng, Hung-yi Lee, Jyh-Shing Roger Jang:
Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection. SLT 2022: 692-699 - [c140]Yi-Jen Shih, Hsuan-Fu Wang, Heng-Jui Chang, Layne Berry, Hung-yi Lee, David Harwath:
SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model. SLT 2022: 715-722 - [c139]Tzu-hsun Feng, Shuyan Annie Dong, Ching-Feng Yeh, Shu-Wen Yang, Tzu-Quan Lin, Jiatong Shi, Kai-Wei Chang, Zili Huang, Haibin Wu, Xuankai Chang, Shinji Watanabe, Abdelrahman Mohamed, Shang-Wen Li, Hung-yi Lee:
Superb @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning. SLT 2022: 1096-1103 - [c138]Guan-Ting Lin, Chi-Luen Feng, Wei-Ping Huang, Yuan Tseng, Tzu-Han Lin, Chen-An Li, Hung-yi Lee, Nigel G. Ward:
On the Utility of Self-Supervised Models for Prosody-Related Tasks. SLT 2022: 1104-1111 - [c137]Kuan-Po Huang, Yu-Kuan Fu, Tsu-Yuan Hsu, Fabian Ritter Gutierrez, Fan-Lin Wang, Liang-Hsuan Tseng, Yu Zhang, Hung-yi Lee:
Improving Generalizability of Distilled Self-Supervised Speech Processing Models Under Distorted Settings. SLT 2022: 1112-1119 - [c136]Zih-Ching Chen, Chin-Lun Fu, Chih-Ying Liu, Shang-Wen (Daniel) Li, Hung-yi Lee:
Exploring Efficient-Tuning Methods in Self-Supervised Speech Models. SLT 2022: 1120-1127 - [c135]Yen Meng, Hsuan-Jui Chen, Jiatong Shi, Shinji Watanabe, Paola García, Hung-yi Lee, Hao Tang:
On Compressing Sequences for Self-Supervised Speech Models. SLT 2022: 1128-1135 - [e1]Kong Aik Lee, Hung-yi Lee, Yanfeng Lu, Minghui Dong:
13th International Symposium on Chinese Spoken Language Processing, ISCSLP 2022, Singapore, December 11-14, 2022. IEEE 2022, ISBN 979-8-3503-9796-3 [contents] - [i183]Chih-Chiang Chang, Shun-Po Chuang, Hung-yi Lee:
Anticipation-free Training for Simultaneous Translation. CoRR abs/2201.12868 (2022) - [i182]Haibin Wu, Heng-Cheng Kuo, Naijun Zheng, Kuo-Hsuan Hung, Hung-Yi Lee, Yu Tsao, Hsin-Min Wang, Helen Meng:
Partially Fake Audio Detection by Self-attention-based Fake Span Discovery. CoRR abs/2202.06684 (2022) - [i181]Guan-Ting Lin, Yung-Sung Chuang, Ho-Lam Chung, Shu-Wen Yang, Hsuan-Jui Chen, Shuyan Dong, Shang-Wen Li, Abdelrahman Mohamed, Hung-yi Lee, Lin-Shan Lee:
DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering. CoRR abs/2203.04911 (2022) - [i180]Kuan-Po Huang, Yuan-Kuei Wu, Hung-yi Lee:
Improving the transferability of speech separation by meta-learning. CoRR abs/2203.05882 (2022) - [i179]Hsiang-Sheng Tsai, Heng-Jui Chang, Wen-Chin Huang, Zili Huang, Kushal Lakhotia, Shu-Wen Yang, Shuyan Dong, Andy T. Liu, Cheng-I Jeff Lai, Jiatong Shi, Xuankai Chang, Phil Hall, Hsuan-Jui Chen, Shang-Wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-yi Lee:
SUPERB-SG: Enhanced Speech processing Universal PERformance Benchmark for Semantic and Generative Capabilities. CoRR abs/2203.06849 (2022) - [i178]Guan-Ting Lin, Shang-Wen Li, Hung-yi Lee:
Listen, Adapt, Better WER: Source-free Single-utterance Test-time Adaptation for Automatic Speech Recognition. CoRR abs/2203.14222 (2022) - [i177]Yang Zhang, Zhiqiang Lv, Haibin Wu, Shanshan Zhang, Pengfei Hu, Zhiyong Wu, Hung-Yi Lee, Helen Meng:
MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification. CoRR abs/2203.15249 (2022) - [i176]Haibin Wu, Lingwei Meng, Jiawen Kang, Jinchao Li, Xu Li, Xixin Wu, Hung-yi Lee, Helen Meng:
Spoofing-Aware Speaker Verification by Multi-Level Fusion. CoRR abs/2203.15377 (2022) - [i175]Kuan-Po Huang, Yu-Kuan Fu, Yu Zhang, Hung-yi Lee:
Improving Distortion Robustness of Self-supervised Speech Processing Tasks with Domain Adaptation. CoRR abs/2203.16104 (2022) - [i174]Kai-Wei Chang, Wei-Cheng Tseng, Shang-Wen Li, Hung-yi Lee:
An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks. CoRR abs/2203.16773 (2022) - [i173]Fan-Lin Wang, Po-Chun Hsu, Da-Rong Liu, Hung-yi Lee:
Universal Adaptor: Converting Mel-Spectrograms Between Different Configurations for Speech Synthesis. CoRR abs/2204.00170 (2022) - [i172]Wei-Tsung Kao, Yuen-Kwei Wu, Chia-Ping Chen, Zhi-Sheng Chen, Yu-Pao Tsai, Hung-Yi Lee:
On the Efficiency of Integrating Self-supervised Learning and Meta-learning for User-defined Few-shot Keyword Spotting. CoRR abs/2204.00352 (2022) - [i171]Wei-Cheng Tseng, Wei-Tsung Kao, Hung-yi Lee:
DDOS: A MOS Prediction Framework utilizing Domain Adaptive Pre-training and Distribution of Opinion Scores. CoRR abs/2204.03219 (2022) - [i170]David Cheng-Han Chiang, Hung-Yi Lee:
Understanding, Detecting, and Separating Out-of-Distribution Samples and Adversarial Samples in Text Classification. CoRR abs/2204.04458 (2022) - [i169]David Cheng-Han Chiang, Hung-Yi Lee:
Re-Examining Human Annotations for Interpretable NLP. CoRR abs/2204.04580 (2022) - [i168]Chan-Jan Hsu, Hung-yi Lee, Yu Tsao:
XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding. CoRR abs/2204.07316 (2022) - [i167]Chih-Chiang Chang, Hung-yi Lee:
Exploring Continuous Integrate-and-Fire for Adaptive Simultaneous Speech Translation. CoRR abs/2204.09595 (2022) - [i166]Po-Chun Hsu, Da-Rong Liu, Andy T. Liu, Hung-yi Lee:
Parallel Synthesis for Autoregressive Speech Generation. CoRR abs/2204.11806 (2022) - [i165]Chin-Lun Fu, Zih-Ching Chen, Yun-Ru Lee, Hung-yi Lee:
AdapterBias: Parameter-efficient Token-dependent Representation Shift for Adapters in NLP Tasks. CoRR abs/2205.00305 (2022) - [i164]Hung-yi Lee, Shang-Wen Li, Ngoc Thang Vu:
Meta Learning for Natural Language Processing: A Survey. CoRR abs/2205.01500 (2022) - [i163]Chi-Luen Feng, Po-Chun Hsu, Hung-yi Lee:
Silence is Sweeter Than Speech: Self-Supervised Model Using Silence to Store Speaker Information. CoRR abs/2205.03759 (2022) - [i162]Abdelrahman Mohamed, Hung-yi Lee, Lasse Borgholt, Jakob D. Havtorn, Joakim Edin, Christian Igel, Katrin Kirchhoff, Shang-Wen Li, Karen Livescu, Lars Maaløe, Tara N. Sainath, Shinji Watanabe:
Self-Supervised Speech Representation Learning: A Review. CoRR abs/2205.10643 (2022) - [i161]Chi-Liang Liu, Hung-yi Lee, Wen-tau Yih:
Structured Prompt Tuning. CoRR abs/2205.12309 (2022) - [i160]Dennis Y. Menn, Hung-yi Lee:
Searching for the Essence of Adversarial Perturbations. CoRR abs/2205.15357 (2022) - [i159]Hsuan Su, Po-Han Chi, Shih-Cheng Huang, Ho-Lam Chung, Saurav Sahay, Shang-Tse Chen, Hung-Yi Lee:
Few-shot Prompting Towards Controllable Response Generation. CoRR abs/2206.03931 (2022) - [i158]Haibin Wu, Jiawen Kang, Lingwei Meng, Yang Zhang, Xixin Wu, Zhiyong Wu, Hung-yi Lee, Helen Meng:
Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion. CoRR abs/2206.09131 (2022) - [i157]Wei-Ping Huang, Po-Chun Chen, Sung-Feng Huang, Hung-yi Lee:
Few-Shot Cross-Lingual TTS Using Transferable Phoneme Embedding. CoRR abs/2206.15427 (2022) - [i156]Da-Rong Liu, Po-Chun Hsu, Yi-Chen Chen, Sung-Feng Huang, Shun-Po Chuang, Da-Yi Wu, Hung-yi Lee:
Learning Phone Recognition from Unpaired Audio and Phone Sequences Based on Generative Adversarial Network. CoRR abs/2207.14568 (2022) - [i155]Tung-Yu Wu, Chen-An Li, Tzu-Han Lin, Tsu-Yuan Hsu, Hung-Yi Lee:
The Ability of Self-Supervised Speech Models for Audio Representations. CoRR abs/2209.12900 (2022) - [i154]Yi-Jen Shih, Hsuan-Fu Wang, Heng-Jui Chang, Layne Berry, Hung-yi Lee, David Harwath:
SpeechCLIP: Integrating Speech with Pre-Trained Vision and Language Model. CoRR abs/2210.00705 (2022) - [i153]Xuanjun Chen, Haibin Wu, Helen Meng, Hung-yi Lee, Jyh-Shing Roger Jang:
Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detection. CoRR abs/2210.00753 (2022) - [i152]David Cheng-Han Chiang, Hung-yi Lee:
How Far Are We from Real Synonym Substitution Attacks? CoRR abs/2210.02844 (2022) - [i151]Zih-Ching Chen, Chin-Lun Fu, Chih-Ying Liu, Shang-Wen Li, Hung-yi Lee:
Exploring Efficient-tuning Methods in Self-supervised Speech Models. CoRR abs/2210.06175 (2022) - [i150]Guan-Ting Lin, Chi-Luen Feng, Wei-Ping Huang, Yuan Tseng, Tzu-Han Lin, Chen-An Li, Hung-yi Lee, Nigel G. Ward:
On the Utility of Self-supervised Models for Prosody-related Tasks. CoRR abs/2210.07185 (2022) - [i149]Yen Meng, Hsuan-Jui Chen, Jiatong Shi, Shinji Watanabe, Paola García, Hung-yi Lee, Hao Tang:
On Compressing Sequences for Self-Supervised Speech Models. CoRR abs/2210.07189 (2022) - [i148]Kuan-Po Huang, Yu-Kuan Fu, Tsu-Yuan Hsu, Fabian Ritter Gutierrez, Fan-Lin Wang, Liang-Hsuan Tseng, Yu Zhang, Hung-yi Lee:
Improving generalizability of distilled self-supervised speech processing models under distorted settings. CoRR abs/2210.07978 (2022) - [i147]Tzu-hsun Feng, Shuyan Annie Dong, Ching-Feng Yeh, Shu-Wen Yang, Tzu-Quan Lin, Jiatong Shi, Kai-Wei Chang, Zili Huang, Haibin Wu, Xuankai Chang, Shinji Watanabe, Abdelrahman Mohamed, Shang-Wen Li, Hung-yi Lee:
SUPERB @ SLT 2022: Challenge on Generalization and Efficiency of Self-Supervised Speech Representation Learning. CoRR abs/2210.08634 (2022) - [i146]Xuanjun Chen, Haibin Wu, Chung-Che Wang, Hung-yi Lee, Jyh-Shing Roger Jang:
Multimodal Transformer Distillation for Audio-Visual Synchronization. CoRR abs/2210.15563 (2022) - [i145]Chan-Jan Hsu, Ho-Lam Chung, Hung-yi Lee, Yu Tsao:
T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language Understanding via Phoneme level T5. CoRR abs/2211.00586 (2022) - [i144]Layne Berry, Yi-Jen Shih, Hsuan-Fu Wang, Heng-Jui Chang, Hung-yi Lee, David Harwath:
M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to Image Retrieval. CoRR abs/2211.01180 (2022) - [i143]Hsuan-Jui Chen, Yen Meng, Hung-yi Lee:
Once-for-All Sequence Compression for Self-Supervised Speech Models. CoRR abs/2211.02332 (2022) - [i142]Jiatong Shi, Chan-Jan Hsu, Ho-Lam Chung, Dongji Gao, Paola García, Shinji Watanabe, Ann Lee, Hung-yi Lee:
Bridging Speech and Textual Pre-trained Models with Unsupervised ASR. CoRR abs/2211.03025 (2022) - [i141]Derek Xu, Shuyan Dong, Changhan Wang, Suyoun Kim, Zhaojiang Lin, Akshat Shrivastava, Shang-Wen Li, Liang-Hsuan Tseng, Alexei Baevski, Guan-Ting Lin, Hung-yi Lee, Yizhou Sun, Wei Wang:
Introducing Semantics into Speech Encoders. CoRR abs/2211.08402 (2022) - [i140]Tzu-Quan Lin, Hung-yi Lee, Hao Tang:
MelHuBERT: A simplified HuBERT on Mel spectrogram. CoRR abs/2211.09944 (2022) - [i139]Tzu-Quan Lin, Tsung-Huan Yang, Chun-Yao Chang, Kuang-Ming Chen, Tzu-hsun Feng, Hung-yi Lee, Hao Tang:
Compressing Transformer-based self-supervised models for speech processing. CoRR abs/2211.09949 (2022) - [i138]Tsu-Yuan Hsu, Chen-An Li, Tung-Yu Wu, Hung-yi Lee:
Model Extraction Attack against Self-supervised Speech Models. CoRR abs/2211.16044 (2022) - [i137]Dongji Gao, Jiatong Shi, Shun-Po Chuang, Leibny Paola García, Hung-yi Lee, Shinji Watanabe, Sanjeev Khudanpur:
EURO: ESPnet Unsupervised ASR Open-source Toolkit. CoRR abs/2211.17196 (2022) - [i136]Shih-Cheng Huang, Shih-Heng Wang, Min-Han Shih, Saurav Sahay, Hung-yi Lee:
General Framework for Self-Supervised Model Priming for Parameter-Efficient Fine-tuning. CoRR abs/2212.01032 (2022) - [i135]Zih-Ching Chen, Yu-Shun Sung, Hung-yi Lee:
CHAPTER: Exploiting Convolutional Neural Network Adapters for Self-supervised Speech Models. CoRR abs/2212.01282 (2022) - [i134]Suwon Shon, Siddhant Arora, Chyi-Jiunn Lin, Ankita Pasad, Felix Wu, Roshan S. Sharma, Wei-Lun Wu, Hung-Yi Lee, Karen Livescu, Shinji Watanabe:
SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Tasks. CoRR abs/2212.10525 (2022) - 2021
- [j16]Shun-Po Chuang, Alexander H. Liu, Tzu-Wei Sung, Hung-yi Lee:
Improving Automatic Speech Recognition and Speech Translation via Word Embedding Prediction. IEEE ACM Trans. Audio Speech Lang. Process. 29: 93-105 (2021) - [j15]Andy T. Liu, Shang-Wen Li, Hung-yi Lee:
TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech. IEEE ACM Trans. Audio Speech Lang. Process. 29: 2351-2366 (2021) - [c134]Yu-Ching Chiu, Bo-Hao Chang, Tzu-Yu Chen, Cheng-Fu Yang, Nanyi Bi, Richard Tzong-Han Tsai, Hung-yi Lee, Jane Yung-jen Hsu:
Multi-modal User Intent Classification Under the Scenario of Smart Factory (Student Abstract). AAAI 2021: 15771-15772 - [c133]Shun-Po Chuang, Yung-Sung Chuang, Chih-Chiang Chang, Hung-yi Lee:
Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation. ACL/IJCNLP (Findings) 2021: 1068-1077 - [c132]Xuankai Chang, Takashi Maekaku, Pengcheng Guo, Jing Shi, Yen-Ju Lu, Aswin Shanmugam Subramanian, Tianzi Wang, Shu-Wen Yang, Yu Tsao, Hung-yi Lee, Shinji Watanabe:
An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition. ASRU 2021: 228-235 - [c131]Shun-Po Chuang, Heng-Jui Chang, Sung-Feng Huang, Hung-yi Lee:
Non-Autoregressive Mandarin-English Code-Switching Speech Recognition. ASRU 2021: 465-472 - [c130]Wei-Tsung Kao, Hung-yi Lee:
Is BERT a Cross-Disciplinary Knowledge Learner? A Surprising Finding of Pre-trained Models' Transferability. EMNLP (Findings) 2021: 2195-2208 - [c129]Tung-Yu Wu, Tsu-Yuan Hsu, Chen-An Li, Tzu-Han Lin, Hung-yi Lee:
The Efficacy of Self-Supervised Speech Models for Audio Representations. HEAR@NeurIPS 2021: 90-110 - [c128]Yuan-Kuei Wu, Kuan-Po Huang, Yu Tsao, Hung-yi Lee:
One Shot Learning for Speech Separation. ICASSP 2021: 5769-5773 - [c127]Yist Y. Lin, Chung-Ming Chien, Jheng-Hao Lin, Hung-yi Lee, Lin-Shan Lee:
Fragmentvc: Any-To-Any Voice Conversion by End-To-End Extracting and Fusing Fine-Grained Voice Fragments with Attention. ICASSP 2021: 5939-5943 - [c126]Yen-Hao Chen, Da-Yi Wu, Tsung-Han Wu, Hung-yi Lee:
Again-VC: A One-Shot Voice Conversion Using Activation Guidance and Adaptive Instance Normalization. ICASSP 2021: 5954-5958 - [c125]Haibin Wu, Xu Li, Andy T. Liu, Zhiyong Wu, Helen Meng, Hung-yi Lee:
Adversarial Defense for Automatic Speaker Verification by Cascaded Self-Supervised Learning Models. ICASSP 2021: 6718-6722 - [c124]Cheng-I Lai, Yung-Sung Chuang, Hung-Yi Lee, Shang-Wen Li, James R. Glass:
Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining. ICASSP 2021: 7468-7472 - [c123]Chung-Ming Chien, Jheng-Hao Lin, Chien-yu Huang, Po-Chun Hsu, Hung-yi Lee:
Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech. ICASSP 2021: 8588-8592 - [c122]Jheng-Hao Lin, Yist Y. Lin, Chung-Ming Chien, Hung-yi Lee:
S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations. Interspeech 2021: 836-840 - [c121]Shu-Wen Yang, Po-Han Chi, Yung-Sung Chuang, Cheng-I Jeff Lai, Kushal Lakhotia, Yist Y. Lin, Andy T. Liu, Jiatong Shi, Xuankai Chang, Guan-Ting Lin, Tzu-Hsien Huang, Wei-Cheng Tseng, Ko-tik Lee, Da-Rong Liu, Zili Huang, Shuyan Dong, Shang-Wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-yi Lee:
SUPERB: Speech Processing Universal PERformance Benchmark. Interspeech 2021: 1194-1198 - [c120]Heng-Jui Chang, Hung-yi Lee, Lin-Shan Lee:
Towards Lifelong Learning of End-to-End ASR. Interspeech 2021: 2551-2555 - [c119]Wei-Cheng Tseng, Chien-yu Huang, Wei-Tsung Kao, Yist Y. Lin, Hung-yi Lee:
Utilizing Self-Supervised Representations for MOS Prediction. Interspeech 2021: 2781-2785 - [c118]Sung-Feng Huang, Shun-Po Chuang, Da-Rong Liu, Yi-Chen Chen, Gene-Ping Yang, Hung-yi Lee:
Stabilizing Label Assignment for Speech Separation by Self-Supervised Pre-Training. Interspeech 2021: 3056-3060 - [c117]Jingsong Wang, Yuxuan He, Chunyu Zhao, Qijie Shao, Wei-Wei Tu, Tom Ko, Hung-yi Lee, Lei Xie:
Auto-KWS 2021 Challenge: Task, Datasets, and Baselines. Interspeech 2021: 4244-4248 - [c116]Haibin Wu, Yang Zhang, Zhiyong Wu, Dong Wang, Hung-yi Lee:
Voting for the Right Answer: Adversarial Defense for Speaker Verification. Interspeech 2021: 4294-4298 - [c115]Hsuan Su, Jiun-Hao Jhan, Fan-Yun Sun, Saurav Sahay, Hung-yi Lee:
Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intention. NAACL-HLT 2021: 1559-1569 - [c114]Heng-Jui Chang, Alexander H. Liu, Hung-yi Lee, Lin-Shan Lee:
End-to-End Whispered Speech Recognition with Frequency-Weighted Approaches and Pseudo Whisper Pre-training. SLT 2021: 186-193 - [c113]Po-Han Chi, Pei-Hung Chung, Tsung-Han Wu, Chun-Cheng Hsieh, Yen-Hao Chen, Shang-Wen Li, Hung-yi Lee:
Audio Albert: A Lite Bert for Self-Supervised Learning of Audio Representation. SLT 2021: 344-350 - [c112]Chung-Ming Chien, Hung-yi Lee:
Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis. SLT 2021: 446-453 - [c111]Tzu-hsien Huang, Jheng-Hao Lin, Hung-yi Lee:
How Far Are We from Robust Voice Conversion: A Survey. SLT 2021: 514-521 - [c110]Chien-yu Huang, Yist Y. Lin, Hung-yi Lee, Lin-Shan Lee:
Defending Your Voice: Adversarial Attack on Voice Conversion. SLT 2021: 552-559 - [i133]Haibin Wu, Xu Li, Andy T. Liu, Zhiyong Wu, Helen Meng, Hung-yi Lee:
Adversarial defense for automatic speaker verification by cascaded self-supervised learning models. CoRR abs/2102.07047 (2021) - [i132]Chung-Ming Chien, Jheng-Hao Lin, Chien-yu Huang, Po-Chun Hsu, Hung-yi Lee:
Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech. CoRR abs/2103.04088 (2021) - [i131]Wei-Tsung Kao, Hung-Yi Lee:
Is BERT a Cross-Disciplinary Knowledge Learner? A Surprising Finding of Pre-trained Models' Transferability. CoRR abs/2103.07162 (2021) - [i130]Hsuan Su, Jiun-Hao Jhan, Fan-Yun Sun, Saurav Sahay, Hung-yi Lee:
Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intention. CoRR abs/2103.16429 (2021) - [i129]Jingsong Wang, Yuxuan He, Chunyu Zhao, Qijie Shao, Wei-Wei Tu, Tom Ko, Hung-yi Lee, Lei Xie:
Auto-KWS 2021 Challenge: Task, Datasets, and Baselines. CoRR abs/2104.00513 (2021) - [i128]Heng-Jui Chang, Hung-yi Lee, Lin-Shan Lee:
Towards Lifelong Learning of End-to-end ASR. CoRR abs/2104.01616 (2021) - [i127]Shun-Po Chuang, Heng-Jui Chang, Sung-Feng Huang, Hung-yi Lee:
Non-autoregressive Mandarin-English Code-switching Speech Recognition with Pinyin Mask-CTC and Word Embedding Regularization. CoRR abs/2104.02258 (2021) - [i126]Jheng-Hao Lin, Yist Y. Lin, Chung-Ming Chien, Hung-yi Lee:
S2VC: A Framework for Any-to-Any Voice Conversion with Self-Supervised Pretrained Representations. CoRR abs/2104.02901 (2021) - [i125]Wei-Cheng Tseng, Chien-yu Huang, Wei-Tsung Kao, Yist Y. Lin, Hung-yi Lee:
Utilizing Self-supervised Representations for MOS Prediction. CoRR abs/2104.03017 (2021) - [i124]Shu-Wen Yang, Po-Han Chi, Yung-Sung Chuang, Cheng-I Jeff Lai, Kushal Lakhotia, Yist Y. Lin, Andy T. Liu, Jiatong Shi, Xuankai Chang, Guan-Ting Lin, Tzu-Hsien Huang, Wei-Cheng Tseng, Ko-tik Lee, Da-Rong Liu, Zili Huang, Shuyan Dong, Shang-Wen Li, Shinji Watanabe, Abdelrahman Mohamed, Hung-yi Lee:
SUPERB: Speech processing Universal PERformance Benchmark. CoRR abs/2105.01051 (2021) - [i123]Yi-Chen Chen, Po-Han Chi, Shu-Wen Yang, Kai-Wei Chang, Jheng-Hao Lin, Sung-Feng Huang, Da-Rong Liu, Chi-Liang Liu, Cheng-Kuang Lee, Hung-yi Lee:
SpeechNet: A Universal Modularized Model for Speech Processing Tasks. CoRR abs/2105.03070 (2021) - [i122]Wei-Cheng Huang, Chien-yu Huang, Hung-yi Lee:
Improving Cross-Lingual Reading Comprehension with Self-Training. CoRR abs/2105.03627 (2021) - [i121]Shun-Po Chuang, Yung-Sung Chuang, Chih-Chiang Chang, Hung-yi Lee:
Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translation. CoRR abs/2105.04840 (2021) - [i120]Haibin Wu, Xu Li, Andy T. Liu, Zhiyong Wu, Helen Meng, Hung-yi Lee:
Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning. CoRR abs/2106.00273 (2021) - [i119]Yung-Sung Chuang, Mingye Gao, Hongyin Luo, James R. Glass, Hung-Yi Lee, Yun-Nung Chen, Shang-Wen Li:
Mitigating Biases in Toxic Language Detection through Invariant Rationalization. CoRR abs/2106.07240 (2021) - [i118]Haibin Wu, Yang Zhang, Zhiyong Wu, Dong Wang, Hung-yi Lee:
Voting for the right answer: Adversarial defense for speaker verification. CoRR abs/2106.07868 (2021) - [i117]Kuan-Po Huang, Yuan-Kuei Wu, Hung-yi Lee:
Multi-accent Speech Separation with One Shot Learning. CoRR abs/2106.11713 (2021) - [i116]Haibin Wu, Po-Chun Hsu, Ji Gao, Shanshan Zhang, Shen Huang, Jian Kang, Zhiyong Wu, Helen Meng, Hung-yi Lee:
Spotting adversarial samples for speaker verification by neural vocoders. CoRR abs/2107.00309 (2021) - [i115]Zih-Yun Chiu, Yi-Lin Tuan, Hung-yi Lee, Li-Chen Fu:
Parallelized Reverse Curriculum Generation. CoRR abs/2108.02128 (2021) - [i114]David Cheng-Han Chiang, Hung-yi Lee:
On the Transferability of Pre-trained Language Models: A Study from Artificial Datasets. CoRR abs/2109.03537 (2021) - [i113]Heng-Jui Chang, Shu-Wen Yang, Hung-yi Lee:
DistilHuBERT: Speech Representation Learning by Layer-wise Distillation of Hidden-unit BERT. CoRR abs/2110.01900 (2021) - [i112]Liang-Hsuan Tseng, Yu-Kuan Fu, Heng-Jui Chang, Hung-yi Lee:
Mandarin-English Code-switching Speech Recognition with Self-supervised Speech Representation Models. CoRR abs/2110.03504 (2021) - [i111]Jiun-Hao Jhan, Chao-Peng Liu, Shyh-Kang Jeng, Hung-Yi Lee:
CheerBots: Chatbots toward Empathy and Emotionusing Reinforcement Learning. CoRR abs/2110.03949 (2021) - [i110]Xuankai Chang, Takashi Maekaku, Pengcheng Guo, Jing Shi, Yen-Ju Lu, Aswin Shanmugam Subramanian, Tianzi Wang, Shu-Wen Yang, Yu Tsao, Hung-yi Lee, Shinji Watanabe:
An Exploration of Self-Supervised Pretrained Representations for End-to-End Speech Recognition. CoRR abs/2110.04590 (2021) - [i109]Wen-Chin Huang, Shu-Wen Yang, Tomoki Hayashi, Hung-Yi Lee, Shinji Watanabe, Tomoki Toda:
S3PRL-VC: Open-source Voice Conversion Framework with Self-supervised Speech Representations. CoRR abs/2110.06280 (2021) - [i108]Chien-yu Huang, Kai-Wei Chang, Hung-yi Lee:
Toward Degradation-Robust Voice Conversion. CoRR abs/2110.07537 (2021) - [i107]Yen Meng, Yi-Hui Chou, Andy T. Liu, Hung-yi Lee:
Don't speak too fast: The impact of data bias on self-supervised speech models. CoRR abs/2110.07957 (2021) - [i106]Yi-Chen Chen, Shu-Wen Yang, Cheng-Kuang Lee, Simon See, Hung-yi Lee:
Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning. CoRR abs/2110.09930 (2021) - [i105]Sung-Feng Huang, Chyi-Jiunn Lin, Hung-yi Lee:
Meta-TTS: Meta-Learning for Few-Shot Speaker Adaptive Text-to-Speech. CoRR abs/2111.04040 (2021) - [i104]Haibin Wu, Bo Zheng, Xu Li, Xixin Wu, Hung-yi Lee, Helen Meng:
Characterizing the adversarial vulnerability of speech self-supervised learning. CoRR abs/2111.04330 (2021) - [i103]Wei-Cheng Tseng, Wei-Tsung Kao, Hung-yi Lee:
Membership Inference Attacks Against Self-supervised Speech Models. CoRR abs/2111.05113 (2021) - 2020
- [j14]Zixing Zhang, Dimitris N. Metaxas, Hung-yi Lee, Björn W. Schuller:
Guest Editorial Special Issue on Adversarial Learning in Computational Intelligence. IEEE Trans. Emerg. Top. Comput. Intell. 4(4): 414-416 (2020) - [c109]Che-Ping Tsai, Hung-yi Lee:
Order-Free Learning Alleviating Exposure Bias in Multi-Label Classification. AAAI 2020: 6038-6045 - [c108]Shun-Po Chuang, Tzu-Wei Sung, Alexander H. Liu, Hung-yi Lee:
Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation. ACL 2020: 5998-6003 - [c107]David Cheng-Han Chiang, Sung-Feng Huang, Hung-yi Lee:
Pretrained Language Model Embryology: The Birth of ALBERT. EMNLP (1) 2020: 6813-6828 - [c106]Chun-Hao Chao, Pin-Lun Hsu, Hung-Yi Lee, Yu-Chiang Frank Wang:
Self-Supervised Deep Learning for Fisheye Image Rectification. ICASSP 2020: 2248-2252 - [c105]Gene-Ping Yang, Szu-Lin Wu, Yao-Wen Mao, Hung-yi Lee, Lin-Shan Lee:
Interrupted and Cascaded Permutation Invariant Training for Speech Separation. ICASSP 2020: 6369-6373 - [c104]Andy T. Liu, Shu-Wen Yang, Po-Han Chi, Po-Chun Hsu, Hung-yi Lee:
Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders. ICASSP 2020: 6419-6423 - [c103]Chung-Yi Li, Pei-Chieh Yuan, Hung-yi Lee:
What Does a Network Layer Hear? Analyzing Hidden Representations of End-to-End ASR Through Speech Synthesis. ICASSP 2020: 6434-6438 - [c102]Haibin Wu, Songxiang Liu, Helen Meng, Hung-yi Lee:
Defense Against Adversarial Attacks on Spoofing Countermeasures of ASV. ICASSP 2020: 6564-6568 - [c101]Alexander H. Liu, Tao Tu, Hung-yi Lee, Lin-Shan Lee:
Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning. ICASSP 2020: 7259-7263 - [c100]Da-Yi Wu, Hung-Yi Lee:
One-Shot Voice Conversion by Vector Quantization. ICASSP 2020: 7734-7738 - [c99]Jui-Yang Hsu, Yuan-Jui Chen, Hung-yi Lee:
Meta Learning for End-To-End Low-Resource Speech Recognition. ICASSP 2020: 7844-7848 - [c98]Alexander H. Liu, Tzu-Wei Sung, Shun-Po Chuang, Hung-yi Lee, Lin-Shan Lee:
Sequence-to-Sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding. ICASSP 2020: 7879-7883 - [c97]Shun-Po Chuang, Tzu-Wei Sung, Hung-yi Lee:
Training Code-Switching Language Model with Monolingual Data. ICASSP 2020: 7949-7953 - [c96]Fan-Keng Sun, Cheng-Hao Ho, Hung-Yi Lee:
LAMOL: LAnguage MOdeling for Lifelong Language Learning. ICLR 2020 - [c95]Po-Chun Hsu, Hung-yi Lee:
WG-WaveNet: Real-Time High-Fidelity Speech Synthesis Without GPU. INTERSPEECH 2020: 210-214 - [c94]Yi-Chen Chen, Jui-Yang Hsu, Cheng-Kuang Lee, Hung-yi Lee:
DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation. INTERSPEECH 2020: 1803-1807 - [c93]Tao Tu, Yuan-Jui Chen, Alexander H. Liu, Hung-yi Lee:
Semi-Supervised Learning for Multi-Speaker Text-to-Speech Synthesis Using Discrete Speech Representation. INTERSPEECH 2020: 3191-3195 - [c92]Haibin Wu, Andy T. Liu, Hung-yi Lee:
Defense for Black-Box Attacks on Anti-Spoofing Models by Self-Supervised Learning. INTERSPEECH 2020: 3780-3784 - [c91]Shu-Wen Yang, Andy T. Liu, Hung-yi Lee:
Understanding Self-Attention of Self-Supervised Audio Transformers. INTERSPEECH 2020: 3785-3789 - [c90]Yung-Sung Chuang, Chi-Liang Liu, Hung-yi Lee, Lin-Shan Lee:
SpeechBERT: An Audio-and-Text Jointly Learned Language Model for End-to-End Spoken Question Answering. INTERSPEECH 2020: 4168-4172 - [c89]Da-Yi Wu, Yen-Hao Chen, Hung-yi Lee:
VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net Architecture. INTERSPEECH 2020: 4691-4695 - [c88]Chun-Hsing Lin, Siang-Ruei Wu, Hung-yi Lee, Yun-Nung Chen:
TaylorGAN: Neighbor-Augmented Policy Update Towards Sample-Efficient Natural Language Generation. NeurIPS 2020 - [i102]Wei-Tsung Kao, Tsung-Han Wu, Po-Han Chi, Chun-Cheng Hsieh, Hung-yi Lee:
Further Boosting BERT-based Models by Duplicating Existing Layers: Some Intriguing Phenomena inside BERT. CoRR abs/2001.09309 (2020) - [i101]Haibin Wu, Songxiang Liu, Helen Meng, Hung-yi Lee:
Defense against adversarial attacks on spoofing countermeasures of ASV. CoRR abs/2003.03065 (2020) - [i100]Chi-Liang Liu, Tsung-Yuan Hsu, Yung-Sung Chuang, Hung-yi Lee:
A Study of Cross-Lingual Ability and Language-specific Information in Multilingual BERT. CoRR abs/2004.09205 (2020) - [i99]Yau-Shian Wang, Hung-yi Lee, Yun-Nung Chen:
Learning Interpretable and Discrete Representations with Adversarial Training for Unsupervised Text Classification. CoRR abs/2004.13255 (2020) - [i98]Heng-Jui Chang, Alexander H. Liu, Hung-yi Lee, Lin-Shan Lee:
End-to-end Whispered Speech Recognition with Frequency-weighted Approaches and Layer-wise Transfer Learning. CoRR abs/2005.01972 (2020) - [i97]Yi-Chen Chen, Jui-Yang Hsu, Cheng-Kuang Lee, Hung-yi Lee:
DARTS-ASR: Differentiable Architecture Search for Multilingual Speech Recognition and Adaptation. CoRR abs/2005.07029 (2020) - [i96]Po-Chun Hsu, Hung-yi Lee:
WG-WaveNet: Real-Time High-Fidelity Speech Synthesis without GPU. CoRR abs/2005.07412 (2020) - [i95]Tao Tu, Yuan-Jui Chen, Alexander H. Liu, Hung-yi Lee:
Semi-supervised Learning for Multi-speaker Text-to-speech Synthesis Using Discrete Speech Representation. CoRR abs/2005.08024 (2020) - [i94]Po-Han Chi, Pei-Hung Chung, Tsung-Han Wu, Chun-Cheng Hsieh, Shang-wen Li, Hung-yi Lee:
Audio ALBERT: A Lite BERT for Self-supervised Learning of Audio Representation. CoRR abs/2005.08575 (2020) - [i93]Chien-yu Huang, Yist Y. Lin, Hung-yi Lee, Lin-Shan Lee:
Defending Your Voice: Adversarial Attack on Voice Conversion. CoRR abs/2005.08781 (2020) - [i92]Yuan-Kuei Wu, Chao-I Tuan, Hung-yi Lee, Yu Tsao:
SADDEL: Joint Speech Separation and Denoising Model based on Multitask Learning. CoRR abs/2005.09966 (2020) - [i91]Shun-Po Chuang, Tzu-Wei Sung, Alexander H. Liu, Hung-yi Lee:
Worse WER, but Better BLEU? Leveraging Word Embedding as Intermediate in Multitask End-to-End Speech Translation. CoRR abs/2005.10678 (2020) - [i90]Haibin Wu, Andy T. Liu, Hung-yi Lee:
Defense for Black-box Attacks on Anti-spoofing Models by Self-Supervised Learning. CoRR abs/2006.03214 (2020) - [i89]Shu-Wen Yang, Andy T. Liu, Hung-yi Lee:
Understanding Self-Attention of Self-Supervised Audio Transformers. CoRR abs/2006.03265 (2020) - [i88]Da-Yi Wu, Yen-Hao Chen, Hung-Yi Lee:
VQVC+: One-Shot Voice Conversion by Vector Quantization and U-Net architecture. CoRR abs/2006.04154 (2020) - [i87]Tsung-Han Wu, Chun-Cheng Hsieh, Yen-Hao Chen, Po-Han Chi, Hung-yi Lee:
Hand-crafted Attention is All You Need? A Study of Attention on Self-supervised Audio Transformer. CoRR abs/2006.05174 (2020) - [i86]Andy T. Liu, Shang-wen Li, Hung-yi Lee:
TERA: Self-Supervised Learning of Transformer Encoder Representation for Speech. CoRR abs/2007.06028 (2020) - [i85]Hung-yi Lee, Cheng-Hao Ho, Chien-Fu Lin, Chiung-Chih Chang, Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen:
Investigation of Sentiment Controllable Chatbot. CoRR abs/2007.07196 (2020) - [i84]David Cheng-Han Chiang, Sung-Feng Huang, Hung-yi Lee:
Pretrained Language Model Embryology: The Birth of ALBERT. CoRR abs/2010.02480 (2020) - [i83]Chi-Liang Liu, Tsung-Yuan Hsu, Yung-Sung Chuang, Chung-Yi Li, Hung-yi Lee:
Language Representation in Multilingual BERT and its applications to improve Cross-lingual Generalization. CoRR abs/2010.10041 (2020) - [i82]Chi-Liang Liu, Tsung-Yuan Hsu, Yung-Sung Chuang, Hung-yi Lee:
What makes multilingual BERT multilingual? CoRR abs/2010.10938 (2020) - [i81]Chi-Liang Liu, Hung-yi Lee:
Unsupervised Deep Learning based Multiple Choices Question Answering: Start Learning from Basic Knowledge. CoRR abs/2010.11003 (2020) - [i80]Cheng-I Lai, Yung-Sung Chuang, Hung-yi Lee, Shang-wen Li, James R. Glass:
Semi-Supervised Spoken Language Understanding via Self-Supervised Speech and Language Model Pretraining. CoRR abs/2010.13826 (2020) - [i79]Yist Y. Lin, Chung-Ming Chien, Jheng-Hao Lin, Hung-yi Lee, Lin-Shan Lee:
FragmentVC: Any-to-Any Voice Conversion by End-to-End Extracting and Fusing Fine-Grained Voice Fragments With Attention. CoRR abs/2010.14150 (2020) - [i78]Sung-Feng Huang, Shun-Po Chuang, Da-Rong Liu, Yi-Chen Chen, Gene-Ping Yang, Hung-yi Lee:
Self-supervised Pre-training Reduces Label Permutation Instability of Speech Separation. CoRR abs/2010.15366 (2020) - [i77]Yen-Hao Chen, Da-Yi Wu, Tsung-Han Wu, Hung-yi Lee:
AGAIN-VC: A One-shot Voice Conversion using Activation Guidance and Adaptive Instance Normalization. CoRR abs/2011.00316 (2020) - [i76]Chung-Ming Chien, Hung-yi Lee:
Hierarchical Prosody Modeling for Non-Autoregressive Speech Synthesis. CoRR abs/2011.06465 (2020) - [i75]Yuan-Kuei Wu, Kuan-Po Huang, Yu Tsao, Hung-yi Lee:
One Shot Learning for Speech Separation. CoRR abs/2011.10233 (2020) - [i74]Tzu-hsien Huang, Jheng-Hao Lin, Chien-yu Huang, Hung-yi Lee:
How Far Are We from Robust Voice Conversion: A Survey. CoRR abs/2011.12063 (2020) - [i73]Chun-Hsing Lin, Siang-Ruei Wu, Hung-yi Lee, Yun-Nung Chen:
TaylorGAN: Neighbor-Augmented Policy Update for Sample-Efficient Natural Language Generation. CoRR abs/2011.13527 (2020) - [i72]David Cheng-Han Chiang, Hung-yi Lee:
Pre-Training a Language Model Without Human Language. CoRR abs/2012.11995 (2020)
2010 – 2019
- 2019
- [j13]Shun-Yao Shih, Fan-Keng Sun, Hung-Yi Lee:
Temporal pattern attention for multivariate time series forecasting. Mach. Learn. 108(8-9): 1421-1441 (2019) - [j12]Yi-Lin Tuan, Hung-yi Lee:
Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation. IEEE ACM Trans. Audio Speech Lang. Process. 27(4): 788-798 (2019) - [j11]Chia-Hsuan Lee, Hung-yi Lee, Szu-Lin Wu, Chi-Liang Liu, Wei Fang, Juei-Yang Hsu, Bo-Hsiang Tseng:
Machine Comprehension of Spoken Content: TOEFL Listening Test and Spoken SQuAD. IEEE ACM Trans. Audio Speech Lang. Process. 27(9): 1469-1480 (2019) - [j10]Yi-Chen Chen, Sung-Feng Huang, Hung-yi Lee, Yu-Hsuan Wang, Chia-Hao Shen:
Audio Word2vec: Sequence-to-Sequence Autoencoding for Unsupervised Learning of Audio Segmentation and Representation. IEEE ACM Trans. Audio Speech Lang. Process. 27(9): 1481-1493 (2019) - [c87]Songxiang Liu, Haibin Wu, Hung-yi Lee, Helen Meng:
Adversarial Attacks on Spoofing Countermeasures of Automatic Speaker Verification. ASRU 2019: 312-319 - [c86]Yau-Shian Wang, Hung-yi Lee, Yun-Nung Chen:
Tree Transformer: Integrating Tree Structures into Self-Attention. EMNLP/IJCNLP (1) 2019: 1061-1070 - [c85]Yi-Lin Tuan, Yun-Nung Chen, Hung-yi Lee:
DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs. EMNLP/IJCNLP (1) 2019: 1855-1865 - [c84]Tsung-Yuan Hsu, Chi-Liang Liu, Hung-yi Lee:
Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model. EMNLP/IJCNLP (1) 2019: 5932-5939 - [c83]Hongren Mao, Hung-yi Lee:
Polly Want a Cracker: Analyzing Performance of Parroting on Paraphrase Generation Datasets. EMNLP/IJCNLP (1) 2019: 5959-5967 - [c82]Chia-Hung Wan, Shun-Po Chuang, Hung-yi Lee:
Towards Audio to Scene Image Synthesis Using Generative Adversarial Network. ICASSP 2019: 496-500 - [c81]Che-Ping Tsai, Hung-yi Lee:
Adversarial Learning of Label Dependency: A Novel Framework for Multi-class Classification. ICASSP 2019: 3847-3851 - [c80]Alexander H. Liu, Hung-yi Lee, Lin-Shan Lee:
Adversarial Training of End-to-end Speech Recognition Using a Criticizing Language Model. ICASSP 2019: 6176-6180 - [c79]Tzu-Wei Sung, Jun-You Liu, Hung-yi Lee, Lin-Shan Lee:
Towards End-to-end Speech-to-text Translation with Two-pass Decoding. ICASSP 2019: 7175-7179 - [c78]Chia-Hsuan Lee, Yun-Nung Chen, Hung-yi Lee:
Mitigating the Impact of Speech Recognition Errors on Spoken Question Answering by Adversarial Domain Adaptation. ICASSP 2019: 7300-7304 - [c77]Richard Tzong-Han Tsai, Chia-Hao Chen, Chun-Kai Wu, Yu-Cheng Hsiao, Hung-yi Lee:
Using Deep-Q Network to Select Candidates from N-best Speech Recognition Hypotheses for Enhancing Dialogue State Tracking. ICASSP 2019: 7375-7379 - [c76]Ching-Ting Chang, Shun-Po Chuang, Hung-yi Lee:
Code-Switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation. INTERSPEECH 2019: 554-558 - [c75]Ju-Chieh Chou, Hung-yi Lee:
One-Shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization. INTERSPEECH 2019: 664-668 - [c74]Li-Wei Chen, Hung-yi Lee, Yu Tsao:
Generative Adversarial Networks for Unpaired Voice Transformation on Impaired Speech. INTERSPEECH 2019: 719-723 - [c73]Andy T. Liu, Po-Chun Hsu, Hung-yi Lee:
Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion. INTERSPEECH 2019: 1108-1112 - [c72]Gene-Ping Yang, Chao-I Tuan, Hung-yi Lee, Lin-Shan Lee:
Improved Speech Separation with Time-and-Frequency Cross-Domain Joint Embedding and Clustering. INTERSPEECH 2019: 1363-1367 - [c71]Kuan-Yu Chen, Che-Ping Tsai, Da-Rong Liu, Hung-yi Lee, Lin-Shan Lee:
Completely Unsupervised Phoneme Recognition by a Generative Adversarial Network Harmonized with Iteratively Refined Hidden Markov Models. INTERSPEECH 2019: 1856-1860 - [c70]Yuan-Jui Chen, Tao Tu, Cheng-chieh Yeh, Hung-yi Lee:
End-to-End Text-to-Speech for Low-Resource Languages by Cross-Lingual Transfer Learning. INTERSPEECH 2019: 2075-2079 - [c69]Chien-Feng Liao, Yu Tsao, Hung-yi Lee, Hsin-Min Wang:
Noise Adaptive Speech Enhancement Using Domain Adversarial Training. INTERSPEECH 2019: 3148-3152 - [c68]Feng-Guang Su, Aliyah R. Hsu, Yi-Lin Tuan, Hung-yi Lee:
Personalized Dialogue Response Generation Learned from Monologues. INTERSPEECH 2019: 4160-4164 - [i71]Kuan-Yu Chen, Che-Ping Tsai, Da-Rong Liu, Hung-yi Lee, Lin-Shan Lee:
Completely Unsupervised Phoneme Recognition By A Generative Adversarial Network Harmonized With Iteratively Refined Hidden Markov Models. CoRR abs/1904.04100 (2019) - [i70]Yi-Chen Chen, Sung-Feng Huang, Hung-yi Lee, Lin-Shan Lee:
From Semi-supervised to Almost-unsupervised Speech Recognition with Very-low Resource by Jointly Learning Phonetic Structures from Audio and Text Embeddings. CoRR abs/1904.05078 (2019) - [i69]Ju-Chieh Chou, Cheng-chieh Yeh, Hung-yi Lee:
One-shot Voice Conversion by Separating Speaker and Content Representations with Instance Normalization. CoRR abs/1904.05742 (2019) - [i68]Tao Tu, Yuan-Jui Chen, Cheng-chieh Yeh, Hung-yi Lee:
End-to-end Text-to-speech for Low-resource Languages by Cross-Lingual Transfer Learning. CoRR abs/1904.06508 (2019) - [i67]Gene-Ping Yang, Chao-I Tuan, Hung-yi Lee, Lin-Shan Lee:
Improved Speech Separation with Time-and-Frequency Cross-domain Joint Embedding and Clustering. CoRR abs/1904.07845 (2019) - [i66]Chia-Hsuan Lee, Yun-Nung Chen, Hung-yi Lee:
Mitigating the Impact of Speech Recognition Errors on Spoken Question Answering by Adversarial Domain Adaptation. CoRR abs/1904.07904 (2019) - [i65]Andy T. Liu, Po-Chun Hsu, Hung-yi Lee:
Unsupervised End-to-End Learning of Discrete Linguistic Units for Voice Conversion. CoRR abs/1905.11563 (2019) - [i64]Chia-Hsuan Lee, Hung-yi Lee:
Cross-Lingual Transfer Learning for Question Answering. CoRR abs/1907.06042 (2019) - [i63]Hongren Mao, Hung-yi Lee:
Polly Want a Cracker: Analyzing Performance of Parroting on Paraphrase Generation Datasets. CoRR abs/1908.07831 (2019) - [i62]Fan-Keng Sun, Cheng-Hao Ho, Hung-Yi Lee:
LAMAL: LAnguage Modeling Is All You Need for Lifelong Language Learning. CoRR abs/1909.03329 (2019) - [i61]Che-Ping Tsai, Hung-yi Lee:
Order-free Learning Alleviating Exposure Bias in Multi-label Classification. CoRR abs/1909.03434 (2019) - [i60]Yau-Shian Wang, Hung-yi Lee, Yun-Nung Chen:
Tree Transformer: Integrating Tree Structures into Self-Attention. CoRR abs/1909.06639 (2019) - [i59]Tsung-Yuan Hsu, Chi-Liang Liu, Hung-yi Lee:
Zero-shot Reading Comprehension by Cross-lingual Transfer Learning with Multi-lingual Language Representation Model. CoRR abs/1909.09587 (2019) - [i58]Yi-Lin Tuan, Yun-Nung Chen, Hung-yi Lee:
DyKgChat: Benchmarking Dialogue Generation Grounding on Dynamic Knowledge Graphs. CoRR abs/1910.00610 (2019) - [i57]Songxiang Liu, Haibin Wu, Hung-yi Lee, Helen Meng:
Adversarial Attacks on Spoofing Countermeasures of automatic speaker verification. CoRR abs/1910.08716 (2019) - [i56]Yung-Sung Chuang, Chi-Liang Liu, Hung-yi Lee:
SpeechBERT: Cross-Modal Pre-trained Language Model for End-to-end Spoken Question Answering. CoRR abs/1910.11559 (2019) - [i55]Jui-Yang Hsu, Yuan-Jui Chen, Hung-yi Lee:
Meta Learning for End-to-End Low-Resource Speech Recognition. CoRR abs/1910.12094 (2019) - [i54]Andy T. Liu, Shu-Wen Yang, Po-Han Chi, Po-Chun Hsu, Hung-yi Lee:
Mockingjay: Unsupervised Speech Representation Learning with Deep Bidirectional Transformer Encoders. CoRR abs/1910.12638 (2019) - [i53]Gene-Ping Yang, Szu-Lin Wu, Yao-Wen Mao, Hung-yi Lee, Lin-Shan Lee:
Interrupted and cascaded permutation invariant training for speech separation. CoRR abs/1910.12706 (2019) - [i52]Alexander H. Liu, Tao Tu, Hung-yi Lee, Lin-Shan Lee:
Towards Unsupervised Speech Recognition and Synthesis with Quantized Speech Representation Learning. CoRR abs/1910.12729 (2019) - [i51]Alexander H. Liu, Tzu-Wei Sung, Shun-Po Chuang, Hung-yi Lee, Lin-Shan Lee:
Sequence-to-sequence Automatic Speech Recognition with Word Embedding Regularization and Fused Decoding. CoRR abs/1910.12740 (2019) - [i50]Chung-Yi Li, Pei-Chieh Yuan, Hung-yi Lee:
What does a network layer hear? Analyzing hidden representations of end-to-end ASR through speech synthesis. CoRR abs/1911.01102 (2019) - [i49]Shun-Po Chuang, Tzu-Wei Sung, Hung-yi Lee:
Training a code-switching language model with monolingual data. CoRR abs/1911.06003 (2019) - [i48]Ya-Liang Chang, Kuan-Ying Lee, Po-Yu Wu, Hung-yi Lee, Winston H. Hsu:
Deep Long Audio Inpainting. CoRR abs/1911.06476 (2019) - [i47]Bo-Wen Chen, Yen-Min Hsu, Hung-Yi Lee:
J-Net: Randomly weighted U-Net for audio source separation. CoRR abs/1911.12926 (2019) - [i46]Po-Chun Hsu, Chun-hsuan Wang, Andy T. Liu, Hung-yi Lee:
Towards Robust Neural Vocoding for Speech Generation: A Survey. CoRR abs/1912.02461 (2019) - [i45]Chao-I Tuan, Yuan-Kuei Wu, Hung-yi Lee, Yu Tsao:
MITAS: A Compressed Time-Domain Audio Separation Network with Parameter Sharing. CoRR abs/1912.03884 (2019) - 2018
- [j9]Hung-yi Lee, Pei-Hung Chung, Yen-Chen Wu, Tzu-Hsiang Lin, Tsung-Hsien Wen:
Interactive Spoken Content Retrieval by Deep Reinforcement Learning. IEEE ACM Trans. Audio Speech Lang. Process. 26(12): 2447-2459 (2018) - [c67]Yau-Shian Wang, Hung-yi Lee:
Learning to Encode Text as Human-Readable Summaries using Generative Adversarial Networks. EMNLP 2018: 4187-4195 - [c66]Chia-Hao Shen, Janet Y. Sung, Hung-yi Lee:
Language Transfer of Audio Word2Vec: Learning Audio Segment Representations Without Target Language Data. ICASSP 2018: 2231-2235 - [c65]Hsien-Chin Lin, Chi-Yu Yang, Hung-yi Lee, Lin-Shan Lee:
Domain Independent Key Term Extraction from Spoken Content Based on Context and Term Location Information in the Utterances. ICASSP 2018: 6044-6048 - [c64]Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-yi Lee, Lin-Shan Lee:
Scalable Sentiment for Sequence-to-Sequence Chatbot Response with Performance Analysis. ICASSP 2018: 6164-6168 - [c63]Chia-Wei Ao, Hung-yi Lee:
Query-by-Example Spoken Term Detection Using Attention-Based Multi-Hop Networks. ICASSP 2018: 6264-6268 - [c62]Yu-Hsuan Wang, Hung-yi Lee, Lin-Shan Lee:
Segmental Audio Word2Vec: Representing Utterances as Sequences of Vectors with Applications in Spoken Term Detection. ICASSP 2018: 6269-6273 - [c61]Ju-Chieh Chou, Cheng-chieh Yeh, Hung-yi Lee, Lin-Shan Lee:
Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations. INTERSPEECH 2018: 501-505 - [c60]Pei-Hung Chung, Kuan Tung, Ching-Lun Tai, Hung-yi Lee:
Joint Learning of Interactive Spoken Content Retrieval and Trainable User Simulator. INTERSPEECH 2018: 2032-2036 - [c59]Chia-Hsuan Li, Szu-Lin Wu, Chi-Liang Liu, Hung-yi Lee:
Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension. INTERSPEECH 2018: 3459-3463 - [c58]Da-Rong Liu, Kuan-Yu Chen, Hung-yi Lee, Lin-Shan Lee:
Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings. INTERSPEECH 2018: 3748-3752 - [c57]Yu-An Chung, Hung-yi Lee, James R. Glass:
Supervised and Unsupervised Transfer Learning for Question Answering. NAACL-HLT 2018: 1585-1594 - [c56]Cheng-chieh Yeh, Po-Chun Hsu, Ju-Chieh Chou, Hung-yi Lee, Lin-Shan Lee:
Rhythm-Flexible Voice Conversion Without Parallel Data Using Cycle-GAN Over Phoneme Posteriorgram Sequences. SLT 2018: 274-281 - [c55]Da-Rong Liu, Chi-Yu Yang, Szu-Lin Wu, Hung-yi Lee:
Improving Unsupervised Style Transfer in end-to-end Speech Synthesis with end-to-end Speech Recognition. SLT 2018: 640-647 - [c54]Yi-Chen Chen, Sung-Feng Huang, Chia-Hao Shen, Hung-yi Lee, Lin-Shan Lee:
Phonetic-and-Semantic Embedding of Spoken words with Applications in Spoken Content Retrieval. SLT 2018: 941-948 - [c53]Chia-Hsuan Lee, Shang-Ming Wang, Huan-Cheng Chang, Hung-yi Lee:
ODSQA: Open-Domain Spoken Question Answering Dataset. SLT 2018: 949-956 - [i44]Yi-Chen Chen, Chia-Hao Shen, Sung-Feng Huang, Hung-yi Lee:
Towards Unsupervised Automatic Speech Recognition Trained by Unaligned Speech and Text only. CoRR abs/1803.10952 (2018) - [i43]Da-Rong Liu, Kuan-Yu Chen, Hung-yi Lee, Lin-Shan Lee:
Completely Unsupervised Phoneme Recognition by Adversarially Learning Mapping Relationships from Audio Embeddings. CoRR abs/1804.00316 (2018) - [i42]Pei-Hung Chung, Kuan Tung, Ching-Lun Tai, Hung-yi Lee:
Joint Learning of Interactive Spoken Content Retrieval and Trainable User Simulator. CoRR abs/1804.00318 (2018) - [i41]Chia-Hsuan Li, Szu-Lin Wu, Chi-Liang Liu, Hung-yi Lee:
Spoken SQuAD: A Study of Mitigating the Impact of Speech Recognition Errors on Listening Comprehension. CoRR abs/1804.00320 (2018) - [i40]Chih-Wei Lee, Yau-Shian Wang, Tsung-Yuan Hsu, Kuan-Yu Chen, Hung-yi Lee, Lin-Shan Lee:
Scalable Sentiment for Sequence-to-sequence Chatbot Response with Performance Analysis. CoRR abs/1804.02504 (2018) - [i39]Ju-Chieh Chou, Cheng-chieh Yeh, Hung-yi Lee, Lin-Shan Lee:
Multi-target Voice Conversion without Parallel Data by Adversarially Learning Disentangled Audio Representations. CoRR abs/1804.02812 (2018) - [i38]Chien-Feng Liao, Yu Tsao, Hung-yi Lee, Hsin-Min Wang:
Noise Adaptive Speech Enhancement using Domain Adversarial Training. CoRR abs/1807.07501 (2018) - [i37]Yi-Chen Chen, Sung-Feng Huang, Chia-Hao Shen, Hung-yi Lee, Lin-Shan Lee:
Phonetic-and-Semantic Embedding of Spoken Words with Applications in Spoken Content Retrieval. CoRR abs/1807.08089 (2018) - [i36]Yu-Hsuan Wang, Hung-yi Lee, Lin-Shan Lee:
Segmental Audio Word2Vec: Representing Utterances as Sequences of Vectors with Applications in Spoken Term Detection. CoRR abs/1808.02228 (2018) - [i35]Chia-Hsuan Lee, Shang-Ming Wang, Huan-Cheng Chang, Hung-yi Lee:
ODSQA: Open-domain Spoken Question Answering Dataset. CoRR abs/1808.02280 (2018) - [i34]Cheng-chieh Yeh, Po-Chun Hsu, Ju-Chieh Chou, Hung-yi Lee, Lin-Shan Lee:
Rhythm-Flexible Voice Conversion without Parallel Data Using Cycle-GAN over Phoneme Posteriorgram Sequences. CoRR abs/1808.03113 (2018) - [i33]Chia-Hung Wan, Shun-Po Chuang, Hung-yi Lee:
Towards Audio to Scene Image Synthesis using Generative Adversarial Network. CoRR abs/1808.04108 (2018) - [i32]Yi-Lin Tuan, Hung-yi Lee:
Improving Conditional Sequence Generative Adversarial Networks by Stepwise Evaluation. CoRR abs/1808.05599 (2018) - [i31]Yi-Lin Tuan, Jinzhi Zhang, Yujia Li, Hung-yi Lee:
Proximal Policy Optimization and its Dynamic Version for Sequence Generation. CoRR abs/1808.07982 (2018) - [i30]Shun-Yao Shih, Fan-Keng Sun, Hung-Yi Lee:
Temporal Pattern Attention for Multivariate Time Series Forecasting. CoRR abs/1809.04206 (2018) - [i29]Yau-Shian Wang, Hung-yi Lee:
Learning to Encode Text as Human-Readable Summaries using Generative Adversarial Networks. CoRR abs/1810.02851 (2018) - [i28]Yi-Chen Chen, Chia-Hao Shen, Sung-Feng Huang, Hung-yi Lee, Lin-Shan Lee:
Almost-unsupervised Speech Recognition with Close-to-zero Resource Based on Phonetic Structures Learned from Very Small Unpaired Speech and Text Data. CoRR abs/1810.12566 (2018) - [i27]Li-Wei Chen, Hung-yi Lee, Yu Tsao:
Generative Adversarial Networks for Unpaired Voice Transformation on Impaired Speech. CoRR abs/1810.12656 (2018) - [i26]Alexander H. Liu, Hung-yi Lee, Lin-Shan Lee:
Adversarial Training of End-to-end Speech Recognition Using a Criticizing Language Model. CoRR abs/1811.00787 (2018) - [i25]Ching-Ting Chang, Shun-Po Chuang, Hung-yi Lee:
Code-switching Sentence Generation by Generative Adversarial Networks and its Application to Data Augmentation. CoRR abs/1811.02356 (2018) - [i24]Sung-Feng Huang, Yi-Chen Chen, Hung-yi Lee, Lin-Shan Lee:
Improved Audio Embeddings by Adjacency-Based Clustering with Applications in Spoken Term Detection. CoRR abs/1811.02775 (2018) - [i23]Che-Ping Tsai, Hung-yi Lee:
Adversarial Learning of Label Dependency: A Novel Framework for Multi-class Classification. CoRR abs/1811.04689 (2018) - 2017
- [j8]Hung-yi Lee, Bo-Hsiang Tseng, Tsung-Hsien Wen, Yu Tsao:
Personalizing Recurrent-Neural-Network-Based Language Model by Social Network. IEEE ACM Trans. Audio Speech Lang. Process. 25(3): 519-530 (2017) - [c52]Shun-Po Chuang, Chia-Hung Wan, Pang-Chi Huang, Chi-Yu Yang, Hung-yi Lee:
Seeing and hearing too: Audio representation for video captioning. ASRU 2017: 381-388 - [c51]Pin-Jung Chen, I-Hung Hsu, Yi Yao Huang, Hung-yi Lee:
Mitigating the impact of speech recognition errors on chatbot using sequence-to-sequence model. ASRU 2017: 497-503 - [c50]Zih-Wei Lin, Tzu-Wei Sung, Hung-yi Lee, Lin-Shan Lee:
Personalized word representations carrying personalized semantics learned from social network posts. ASRU 2017: 533-540 - [c49]Tzu-Ray Su, Hung-yi Lee:
Learning Chinese Word Representations From Glyphs Of Characters. EMNLP 2017: 264-273 - [c48]Cheng-Kuang Wei, Cheng-Tao Chung, Hung-yi Lee, Lin-Shan Lee:
Personalized acoustic modeling by weakly supervised multi-task deep learning using acoustic tokens discovered from unlabeled data. ICASSP 2017: 5165-5169 - [c47]Wei-Jen Ko, Bo-Hsiang Tseng, Hung-yi Lee:
Recurrent Neural Network based language modeling with controllable external Memory. ICASSP 2017: 5705-5709 - [c46]Bo-Ru Lu, Frank Shyu, Yun-Nung Chen, Hung-yi Lee, Lin-Shan Lee:
Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification. INTERSPEECH 2017: 2899-2903 - [c45]Yu-Hsuan Wang, Cheng-Tao Chung, Hung-yi Lee:
Gate Activation Signal Analysis for Gated Recurrent Neural Networks and its Correlation with Phoneme Boundaries. INTERSPEECH 2017: 3822-3826 - [i22]Yu-Hsuan Wang, Cheng-Tao Chung, Hung-yi Lee:
Gate Activation Signal Analysis for Gated Recurrent Neural Networks and Its Correlation with Phoneme Boundaries. CoRR abs/1703.07588 (2017) - [i21]Cheng-Kuang Wei, Cheng-Tao Chung, Hung-yi Lee, Lin-Shan Lee:
Personalized Acoustic Modeling by Weakly Supervised Multi-Task Deep Learning using Acoustic Tokens Discovered from Unlabeled Data. CoRR abs/1706.07793 (2017) - [i20]Chia-Hao Shen, Janet Y. Sung, Hung-yi Lee:
Language Transfer of Audio Word2Vec: Learning Audio Segment Representations without Target Language Data. CoRR abs/1707.06519 (2017) - [i19]Tzu-Ray Su, Hung-yi Lee:
Learning Chinese Word Representations From Glyphs Of Characters. CoRR abs/1708.04755 (2017) - [i18]Chia-Wei Ao, Hung-yi Lee:
Query-by-example Spoken Term Detection using Attention-based Multi-hop Networks. CoRR abs/1709.00354 (2017) - [i17]Tzu-Chien Liu, Yu-Hsueh Wu, Hung-yi Lee:
Attention-based CNN Matching Net. CoRR abs/1709.05036 (2017) - [i16]Bo-Ru Lu, Frank Shyu, Yun-Nung Chen, Hung-yi Lee, Lin-Shan Lee:
Order-Preserving Abstractive Summarization for Spoken Content Based on Connectionist Temporal Classification. CoRR abs/1709.05475 (2017) - [i15]Pin-Jung Chen, I-Hung Hsu, Yi Yao Huang, Hung-yi Lee:
Mitigating the Impact of Speech Recognition Errors on Chatbot using Sequence-to-sequence Model. CoRR abs/1709.07862 (2017) - [i14]Zih-Wei Lin, Tzu-Wei Sung, Hung-yi Lee, Lin-Shan Lee:
Personalized word representations Carrying Personalized Semantics Learned from Social Network Posts. CoRR abs/1710.10574 (2017) - [i13]Yu-An Chung, Hung-yi Lee, James R. Glass:
Supervised and Unsupervised Transfer Learning for Question Answering. CoRR abs/1711.05345 (2017) - 2016
- [c44]Yu-An Chung, Chao-Chung Wu, Chia-Hao Shen, Hung-yi Lee, Lin-Shan Lee:
Audio Word2Vec: Unsupervised Learning of Audio Segment Representations Using Sequence-to-Sequence Autoencoder. INTERSPEECH 2016: 765-769 - [c43]Yen-Chen Wu, Tzu-Hsiang Lin, Yang-De Chen, Hung-yi Lee, Lin-Shan Lee:
Interactive Spoken Content Retrieval by Deep Reinforcement Learning. INTERSPEECH 2016: 943-947 - [c42]Sheng-syun Shen, Hung-yi Lee:
Neural Attention Models for Sequence Classification: Analysis and Application to Key Term Extraction and Dialogue Act Detection. INTERSPEECH 2016: 2716-2720 - [c41]Bo-Hsiang Tseng, Sheng-syun Shen, Hung-yi Lee, Lin-Shan Lee:
Towards Machine Comprehension of Spoken Content: Initial TOEFL Listening Comprehension Test by Machine. INTERSPEECH 2016: 2731-2735 - [c40]Lang-Chi Yu, Hung-yi Lee, Lin-Shan Lee:
Abstractive headline generation for spoken content by attentive recurrent neural networks with ASR error modeling. SLT 2016: 151-157 - [c39]Wei Fang, Juei-Yang Hsu, Hung-yi Lee, Lin-Shan Lee:
Hierarchical attention model for improved machine comprehension of spoken content. SLT 2016: 232-238 - [i12]Cheng-Tao Chung, Cheng-Yu Tsai, Hsiang-Hung Lu, Chia-Hsiang Liu, Hung-yi Lee, Lin-Shan Lee:
An Iterative Deep Learning Framework for Unsupervised Discovery of Speech Features and Linguistic Units with Applications on Spoken Term Detection. CoRR abs/1602.00426 (2016) - [i11]Yu-An Chung, Chao-Chung Wu, Chia-Hao Shen, Hung-yi Lee, Lin-Shan Lee:
Audio Word2Vec: Unsupervised Learning of Audio Segment Representations using Sequence-to-sequence Autoencoder. CoRR abs/1603.00982 (2016) - [i10]Sheng-syun Shen, Hung-yi Lee:
Neural Attention Models for Sequence Classification: Analysis and Application to Key Term Extraction and Dialogue Act Detection. CoRR abs/1604.00077 (2016) - [i9]Bo-Hsiang Tseng, Sheng-syun Shen, Hung-yi Lee, Lin-Shan Lee:
Towards Machine Comprehension of Spoken Content: Initial TOEFL Listening Comprehension Test by Machine. CoRR abs/1608.06378 (2016) - [i8]Wei Fang, Juei-Yang Hsu, Hung-yi Lee, Lin-Shan Lee:
Hierarchical Attention Model for Improved Machine Comprehension of Spoken Content. CoRR abs/1608.07775 (2016) - [i7]Yen-Chen Wu, Tzu-Hsiang Lin, Yang-De Chen, Hung-yi Lee, Lin-Shan Lee:
Interactive Spoken Content Retrieval by Deep Reinforcement Learning. CoRR abs/1609.05234 (2016) - [i6]Da-Rong Liu, Shun-Po Chuang, Hung-yi Lee:
Attention-based Memory Selection Recurrent Network for Language Modeling. CoRR abs/1611.08656 (2016) - [i5]Lang-Chi Yu, Hung-yi Lee, Lin-Shan Lee:
Abstractive Headline Generation for Spoken Content by Attentive Recurrent Neural Networks with ASR Error Modeling. CoRR abs/1612.08375 (2016) - 2015
- [j7]Lin-Shan Lee, James R. Glass, Hung-yi Lee, Chun-an Chan:
Spoken Content Retrieval - Beyond Cascading Speech Recognition with Text Retrieval. IEEE ACM Trans. Audio Speech Lang. Process. 23(9): 1389-1420 (2015) - [c38]Bo-Hsiang Tseng, Hung-yi Lee, Lin-Shan Lee:
Personalizing universal recurrent neural network language model with user characteristic features by social network crowdsourcing. ASRU 2015: 84-91 - [c37]Yi-Hsiu Liao, Hung-yi Lee, Lin-Shan Lee:
Towards structured deep neural network for automatic speech recognition. ASRU 2015: 137-144 - [c36]Cheng-Tao Chung, Cheng-Yu Tsai, Hsiang-Hung Lu, Chia-Hsiang Liu, Hung-yi Lee, Lin-Shan Lee:
An iterative deep learning framework for unsupervised discovery of speech features and linguistic units with applications on spoken term detection. ASRU 2015: 245-251 - [c35]Hung-tsung Lu, Yuan-ming Liou, Hung-yi Lee, Lin-Shan Lee:
Semantic retrieval of personal photos using a deep autoencoder fusing visual features with speech annotations represented as word/paragraph vectors. INTERSPEECH 2015: 140-144 - [c34]Sheng-syun Shen, Hung-yi Lee, Shang-wen Li, Victor Zue, Lin-Shan Lee:
Structuring lectures in massive open online courses (MOOCs) for efficient learning by linking similar sections and predicting prerequisites. INTERSPEECH 2015: 1363-1367 - [c33]Ching-feng Yeh, Yuan-ming Liou, Hung-yi Lee, Lin-Shan Lee:
Personalized speech recognizer with keyword-based personalized lexicon and language model using word vector representations. INTERSPEECH 2015: 3521-3525 - [i4]Yi-Hsiu Liao, Hung-yi Lee, Lin-Shan Lee:
Towards Structured Deep Neural Network for Automatic Speech Recognition. CoRR abs/1506.01163 (2015) - [i3]Bo-Hsiang Tseng, Hung-yi Lee, Lin-Shan Lee:
Personalizing a Universal Recurrent Neural Network Language Model with User Characteristic Features by Crowdsouring over Social Networks. CoRR abs/1506.01192 (2015) - [i2]Cheng-Tao Chung, Cheng-Yu Tsai, Hsiang-Hung Lu, Yuan-ming Liou, Yen-Chen Wu, Yen-Ju Lu, Hung-yi Lee, Lin-Shan Lee:
A Multi-layered Acoustic Tokenizing Deep Neural Network (MAT-DNN) for Unsupervised Discovery of Linguistic Units and Generation of High Quality Features. CoRR abs/1506.02327 (2015) - [i1]Yi-Hsiu Liao, Hung-yi Lee, Lin-Shan Lee:
Towards Structured Deep Neural Network for Automatic Speech Recognition. CoRR abs/1511.02506 (2015) - 2014
- [j6]Hung-yi Lee, Po-wei Chou, Lin-Shan Lee:
Improved open-vocabulary spoken content retrieval with word and subword lattices using acoustic feature similarity. Comput. Speech Lang. 28(5): 1045-1065 (2014) - [j5]Hung-yi Lee, Lin-Shan Lee:
Improved Semantic Retrieval of Spoken Content by Document/Query Expansion with Random Walk Over Acoustic Similarity Graphs. IEEE ACM Trans. Audio Speech Lang. Process. 22(1): 80-94 (2014) - [j4]Hung-yi Lee, Sz-Rung Shiang, Ching-feng Yeh, Yun-Nung Chen, Yu Huang, Sheng-yi Kong, Lin-Shan Lee:
Spoken Knowledge Organization by Semantic Structuring and a Prototype Course Lecture System for Personalized Learning. IEEE ACM Trans. Audio Speech Lang. Process. 22(5): 881-896 (2014) - [c32]Hung-yi Lee, Han-Pang Huang, Huan-Kun Hsu:
Lifting motion planning for humanoid robots. CASE 2014: 1174-1179 - [c31]Sz-Rung Shiang, Hung-yi Lee, Lin-Shan Lee:
Spoken question answering using tree-structured conditional random fields and two-layer random walk. INTERSPEECH 2014: 263-267 - [c30]Han Lu, Sheng-syun Shen, Sz-Rung Shiang, Hung-yi Lee, Lin-Shan Lee:
Alignment of spoken utterances with slide content for easier learning with recorded lectures using structured support vector machine (SVM). INTERSPEECH 2014: 1473-1477 - [c29]Yuan-ming Liou, Yi-Sheng Fu, Hung-yi Lee, Lin-Shan Lee:
Semantic retrieval of personal photos using matrix factorization and two-layer random walk fusing sparse speech annotations with visual features. INTERSPEECH 2014: 1762-1766 - [c28]Hung-yi Lee, Yu Zhang, Ekapol Chuangsuwanich, James R. Glass:
Graph-based re-ranking using acoustic feature similarity between search results for spoken term detection on low-resource languages. INTERSPEECH 2014: 2479-2483 - 2013
- [j3]Hung-yi Lee, Lin-Shan Lee:
Enhanced Spoken Term Detection Using Support Vector Machines and Weighted Pseudo Examples. IEEE Trans. Speech Audio Process. 21(6): 1272-1284 (2013) - [c27]Yun-Chiao Li, Hung-yi Lee, Cheng-Tao Chung, Chun-an Chan, Lin-Shan Lee:
Towards unsupervised semantic retrieval of spoken content with query expansion based on automatically discovered acoustic patterns. ASRU 2013: 198-203 - [c26]Hung-yi Lee, Yun-Chiao Li, Cheng-Tao Chung, Lin-Shan Lee:
Enhancing query expansion for semantic retrieval of spoken content with automatically discovered acoustic patterns. ICASSP 2013: 8297-8301 - [c25]Hung-yi Lee, Yu-Yu Chou, Yow-Bang Wang, Lin-Shan Lee:
Unsupervised domain adaptation for spoken document summarization with structured support vector machine. ICASSP 2013: 8347-8351 - [c24]Tsung-Hsien Wen, Hung-yi Lee, Pei-hao Su, Lin-Shan Lee:
Interactive spoken content retrieval by extended query model and continuous state space Markov Decision Process. ICASSP 2013: 8510-8514 - [c23]Hung-yi Lee, Ting-Yao Hu, How Jing, Yun-Fan Chang, Yu Tsao, Yu-Cheng Kao, Tsang-Long Pao:
Ensemble of machine learning and acoustic segment model techniques for speech emotion and autism spectrum disorders recognition. INTERSPEECH 2013: 215-219 - [c22]Ching-feng Yeh, Hung-yi Lee, Lin-Shan Lee:
Speaking rate normalization with lattice-based context-dependent phoneme duration modeling for personalized speech recognizers on mobile devices. INTERSPEECH 2013: 1741-1745 - [c21]Tsung-Hsien Wen, Aaron Heidel, Hung-yi Lee, Yu Tsao, Lin-Shan Lee:
Recurrent neural network based language model personalization by social network crowdsourcing. INTERSPEECH 2013: 2703-2707 - [c20]Sz-Rung Shiang, Hung-yi Lee, Lin-Shan Lee:
Supervised spoken document summarization based on structured support vector machine with utterance clusters as hidden variables. INTERSPEECH 2013: 2728-2732 - 2012
- [j2]Yi-Cheng Pan, Hung-yi Lee, Lin-Shan Lee:
Interactive Spoken Document Retrieval With Suggested Key Terms Ranked by a Markov Decision Process. IEEE Trans. Speech Audio Process. 20(2): 632-645 (2012) - [j1]Hung-yi Lee, Chia-Ping Chen, Lin-Shan Lee:
Integrating Recognition and Retrieval With Relevance Feedback for Spoken Term Detection. IEEE Trans. Speech Audio Process. 20(7): 2095-2110 (2012) - [c19]Ching-feng Yeh, Aaron Heidel, Hung-yi Lee, Lin-Shan Lee:
Recognition of highly imbalanced code-mixed bilingual speech with frame-level language detection based on blurred posteriorgram. ICASSP 2012: 4873-4876 - [c18]Yun-Nung Chen, Yu Huang, Hung-yi Lee, Lin-Shan Lee:
Unsupervised two-stage keyword extraction from spoken documents by topic coherence and support vector machine. ICASSP 2012: 5041-5044 - [c17]Hung-yi Lee, Yun-Nung Chen, Lin-Shan Lee:
Utterance-level latent topic transition modeling for spoken documents and its application in automatic summarization. ICASSP 2012: 5065-5068 - [c16]Tsung-wei Tu, Hung-yi Lee, Yu-Yu Chou, Lin-Shan Lee:
Semantic query expansion and context-based discriminative term modeling for spoken document retrieval. ICASSP 2012: 5085-5088 - [c15]Hung-yi Lee, Po-wei Chou, Lin-Shan Lee:
Open-Vocabulary Retrieval of Spoken Content with Shorter/Longer Queries Considering Word/Subword-based Acoustic Feature Similarity. INTERSPEECH 2012: 2077-2080 - [c14]Hung-yi Lee, Yu-Yu Chou, Yow-Bang Wang, Lin-Shan Lee:
Supervised Spoken Document Summarization jointly Considering Utterance Importance and Redundancy by Structured Support Vector Machine. INTERSPEECH 2012: 2342-2345 - [c13]Tsung-Hsien Wen, Hung-yi Lee, Lin-Shan Lee:
Interactive Spoken Content Retrieval with Different Types of Actions Optimized By a Markov Decision Process. INTERSPEECH 2012: 2458-2461 - [c12]Hung-yi Lee, Tsung-Hsien Wen, Lin-Shan Lee:
Improved semantic retrieval of spoken content by language models enhanced with acoustic similarity graph. SLT 2012: 182-187 - [c11]Tsung-Hsien Wen, Hung-yi Lee, Tai-Yuan Chen, Lin-Shan Lee:
Personalized language modeling by crowd sourcing with social network data for voice access of cloud applications. SLT 2012: 188-193 - 2011
- [c10]Tsung-wei Tu, Hung-yi Lee, Lin-Shan Lee:
Improved spoken term detection using support vector machines with acoustic and context features from pseudo-relevance feedback. ASRU 2011: 383-388 - [c9]Yun-Nung Chen, Chia-Ping Chen, Hung-yi Lee, Chun-an Chan, Lin-Shan Lee:
Improved spoken term detection with graph-based re-ranking in feature space. ICASSP 2011: 5644-5647 - [c8]Hung-yi Lee, Tsung-wei Tu, Chia-Ping Chen, Chao-Yu Huang, Lin-Shan Lee:
Improved spoken term detection using support vector machines based on lattice context consistency. ICASSP 2011: 5648-5651 - 2010
- [c7]Yu-Hui Chen, Chia-Chen Chou, Hung-yi Lee, Lin-Shan Lee:
An initial attempt to improve spoken term detection by learning optimal weights for different indexing features. ICASSP 2010: 5278-5281 - [c6]Hung-yi Lee, Lin-Shan Lee:
Integrating recognition and retrieval with user feedback: A new framework for spoken term detection. ICASSP 2010: 5290-5293 - [c5]Hung-yi Lee, Chia-Ping Chen, Ching-feng Yeh, Lin-Shan Lee:
Improved spoken term detection by discriminative training of acoustic models based on user relevance feedback. INTERSPEECH 2010: 1273-1276 - [c4]Chia-Ping Chen, Hung-yi Lee, Ching-feng Yeh, Lin-Shan Lee:
Improved spoken term detection by feature space pseudo-relevance feedback. INTERSPEECH 2010: 1672-1675 - [c3]Hung-yi Lee, Chia-Ping Chen, Ching-feng Yeh, Lin-Shan Lee:
A framework integrating different relevance feedback scenarios and approaches for spoken term detection. SLT 2010: 389-394
2000 – 2009
- 2009
- [c2]Hung-yi Lee, Yueh-Lien Tang, Hao Tang, Lin-Shan Lee:
Spoken term detection from bilingual spontaneous speech using code-switched lattice-based structures for words and subword units. ASRU 2009: 410-415 - [c1]Chao-Hong Meng, Hung-yi Lee, Lin-Shan Lee:
Improved lattice-based spoken document retrieval by directly learning from the evaluation measures. ICASSP 2009: 4893-4896
Coauthor Index
Shuyan Dong
aka: Shuyan Annie Dong
aka: Shuyan Annie Dong
David F. Harwath
aka: David Harwath
aka: David Harwath
Cheng-I Lai
aka: Cheng-I Jeff Lai
aka: Cheng-I Jeff Lai
[c198] [i269] [i267] [c148] [i181] [c127] [c120] [c114] [c110] [i128] [c105] [c101] [c98] [c90] [i98] [i93] [i79] [c80] [c79] [c72] [c71] [i71] [i70] [i67] [i53] [i52] [i51] [c65] [c64] [c62] [c61] [c58] [c56] [c54] [i43] [i40] [i39] [i37] [i36] [i34] [i28] [i26] [i24] [c50] [c48] [c46] [i21] [i16] [i14] [c44] [c43] [c41] [c40] [c39] [i12] [i11] [i9] [i8] [i7] [i5] [j7] [c38] [c37] [c36] [c35] [c34] [c33] [i4] [i3] [i2] [i1] [j6] [j5] [j4] [c31] [c30] [c29] [j3] [c27] [c26] [c25] [c24] [c22] [c21] [c20] [j2] [j1] [c19] [c18] [c17] [c16] [c15] [c14] [c13] [c12] [c11] [c10] [c9] [c8] [c7] [c6] [c5] [c4] [c3] [c2] [c1]
[j27] [j26] [c203] [c198] [i269] [i259] [i230] [c193] [c191] [c187] [c171] [c170] [i213] [i208] [i206] [i199] [i195] [i192] [i189] [i186] [j21] [c165] [c154] [c150] [c148] [c145] [c139] [c136] [i181] [i179] [i178] [i174] [i164] [i162] [i151] [i147] [i141] [j15] [c124] [c121] [c113] [i124] [i119] [i94] [i86] [i80] [c34]
Helen M. Meng
aka: Helen Meng
aka: Helen Meng
Abdel-rahman Mohamed
aka: Abdelrahman Mohamed
aka: Abdelrahman Mohamed
[j27] [j26] [c221] [c204] [c203] [c202] [c199] [i262] [i261] [i260] [i259] [i254] [i250] [i234] [i230] [i226] [i223] [i221] [c184] [i207] [i203] [i200] [i199] [i187] [j20] [c164] [c163] [c157] [c156] [c153] [c143] [c141] [c139] [i182] [i177] [i176] [i158] [i153] [i147] [i146] [c125] [c116] [i133] [i120] [i118] [i116] [i104] [c102] [c92] [i101] [i90] [c87] [i57]
manage site settings
To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.
Unpaywalled article links
Add open access links from 
to the list of external document links (if available).
Privacy notice: By enabling the option above, your browser will contact the API of unpaywall.org to load hyperlinks to open access articles. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Unpaywall privacy policy.
Archived links via Wayback Machine
For web page which are no longer available, try to retrieve content from the 
of the Internet Archive (if available).
Privacy notice: By enabling the option above, your browser will contact the API of archive.org to check for archived content of web pages that are no longer available. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Internet Archive privacy policy.
Reference lists
Add a list of references from 
, 
, and 
to record detail pages.
load references from crossref.org and opencitations.net
Privacy notice: By enabling the option above, your browser will contact the APIs of crossref.org, opencitations.net, and semanticscholar.org to load article reference information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the Crossref privacy policy and the OpenCitations privacy policy, as well as the AI2 Privacy Policy covering Semantic Scholar.
Citation data
Add a list of citing articles from and to record detail pages.
load citations from opencitations.net
Privacy notice: By enabling the option above, your browser will contact the API of opencitations.net and semanticscholar.org to load citation information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the OpenCitations privacy policy as well as the AI2 Privacy Policy covering Semantic Scholar.
OpenAlex data
Load additional information about publications from 
.
Privacy notice: By enabling the option above, your browser will contact the API of openalex.org to load additional information. Although we do not have any reason to believe that your call will be tracked, we do not have any control over how the remote server uses your data. So please proceed with care and consider checking the information given by OpenAlex.
last updated on 2024-12-12 21:56 CET by the dblp team
all metadata released as open data under CC0 1.0 license
see also: Terms of Use | Privacy Policy | Imprint
dblp was originally created in 1993 at:
since 2018, dblp has been operated and maintained by:
the dblp computer science bibliography is funded and supported by:
