default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDThomas Hain
Person information
- affiliation: University of Sheffield, England, UK
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
showing all ?? records
2020 – today
- 2024
[c175]Chanho Park, Mingjie Chen, Thomas Hain:
Automatic Speech Recognition System-Independent Word Error Rate Estimation. LREC/COLING 2024: 1979-1987- [c174]Amit Meghanani, Thomas Hain:
Improving Acoustic Word Embeddings through Correspondence Training of Self-supervised Speech Representations. EACL (1) 2024: 1959-1967 - [c173]Olga Iakovenko, Thomas Hain:
Methods of Automatic Matrix Language Determination for Code-Switched Speech. EMNLP 2024: 5791-5800 - [c172]George Close, Thomas Hain, Stefan Goetze:
Hallucination in Perceptual Metric-Driven Speech Enhancement Networks. EUSIPCO 2024: 21-25 - [c171]Chanho Park, Hyunsik Kang, Thomas Hain:
Character Error Rate Estimation for Automatic Speech Recognition of Short Utterances. EUSIPCO 2024: 131-135 - [c170]Cong-Thanh Do, Shuhei Imai, Rama Doddipatla, Thomas Hain:
Improving Accented Speech Recognition Using Data Augmentation Based on Unsupervised Text-to-Speech Synthesis. EUSIPCO 2024: 136-140 - [c169]Robert Sutherland, George Close, Thomas Hain, Stefan Goetze, Jon Barker:
Using Speech Foundational Models in Loss Functions for Hearing Aid Speech Enhancement. EUSIPCO 2024: 421-425 - [c168]Rhiannon Mogridge, George Close, Robert Sutherland, Thomas Hain
, Jon Barker, Stefan Goetze, Anton Ragni:
Non-Intrusive Speech Intelligibility Prediction for Hearing-Impaired Users Using Intermediate ASR Features and Human Memory Models. ICASSP 2024: 306-310 - [c167]George Close, William Ravenscroft, Thomas Hain, Stefan Goetze:
Multi-CMGAN+/+: Leveraging Multi-Objective Speech Quality Metric Prediction for Speech Enhancement. ICASSP 2024: 351-355 - [c166]Rehan Ahmad, Muhammad Umar Farooq, Thomas Hain:
Progressive Unsupervised Domain Adaptation for ASR Using Ensemble Models and Multi-Stage Training. ICASSP 2024: 11466-11470 - [c165]William Ravenscroft, Stefan Goetze, Thomas Hain:
Combining Conformer and Dual-Path-Transformer Networks for Single Channel Noisy Reverberant Speech Separation. ICASSP 2024: 11491-11495 - [c164]Amit Meghanani, Thomas Hain:
SCORE: Self-Supervised Correspondence Fine-Tuning for Improved Content Representations. ICASSP 2024: 12086-12090 - [c163]Mingjie Chen, Hezhao Zhang, Yuanchao Li, Jiachen Luo, Wen Wu, Ziyang Ma, Peter Bell, Catherine Lai, Joshua D. Reiss, Lin Wang, Philip C. Woodland, Xie Chen, Huy Phan, Thomas Hain:
1st Place Solution to Odyssey Emotion Recognition Challenge Task1: Tackling Class Imbalance Problem. Odyssey 2024: 260-265 - [i55]Rhiannon Mogridge, George Close, Robert Sutherland, Thomas Hain, Jon Barker, Stefan Goetze, Anton Ragni:
Non-Intrusive Speech Intelligibility Prediction for Hearing-Impaired Users using Intermediate ASR Features and Human Memory Models. CoRR abs/2401.13611 (2024) - [i54]Amit Meghanani, Thomas Hain:
SCORE: Self-supervised Correspondence Fine-tuning for Improved Content Representations. CoRR abs/2403.06260 (2024) - [i53]Amit Meghanani, Thomas Hain:
Improving Acoustic Word Embeddings through Correspondence Training of Self-supervised Speech Representations. CoRR abs/2403.08738 (2024) - [i52]George Close, Thomas Hain, Stefan Goetze:
Hallucination in Perceptual Metric-Driven Speech Enhancement Networks. CoRR abs/2403.11732 (2024) - [i51]Chanho Park, Mingjie Chen, Thomas Hain:
Automatic Speech Recognition System-Independent Word Error Rate Estimation. CoRR abs/2404.16743 (2024) - [i50]Mingjie Chen, Hezhao Zhang, Yuanchao Li, Jiachen Luo, Wen Wu, Ziyang Ma, Peter Bell, Catherine Lai, Joshua D. Reiss, Lin Wang, Philip C. Woodland, Xie Chen, Huy Phan, Thomas Hain:
1st Place Solution to Odyssey Emotion Recognition Challenge Task1: Tackling Class Imbalance Problem. CoRR abs/2405.20064 (2024) - [i49]Ziyang Ma, Mingjie Chen, Hezhao Zhang, Zhisheng Zheng, Wenxi Chen, Xiquan Li, Jiaxin Ye, Xie Chen, Thomas Hain:
EmoBox: Multilingual Multi-corpus Speech Emotion Recognition Toolkit and Benchmark. CoRR abs/2406.07162 (2024) - [i48]William Ravenscroft, George Close, Stefan Goetze, Thomas Hain, Mohammad Soleymanpour, Anurag Chowdhury, Mark C. Fuhs:
Transcription-Free Fine-Tuning of Speech Separation Models for Noisy and Reverberant Multi-Speaker Automatic Speech Recognition. CoRR abs/2406.08914 (2024) - [i47]Amit Meghanani, Thomas Hain:
LASER: Learning by Aligning Self-supervised Representations of Speech for Improving Content-related Tasks. CoRR abs/2406.09153 (2024) - [i46]Cong-Thanh Do, Shuhei Imai, Rama Doddipatla, Thomas Hain:
Improving Accented Speech Recognition using Data Augmentation based on Unsupervised Text-to-Speech Synthesis. CoRR abs/2407.04047 (2024) - [i45]Robert Sutherland, George Close, Thomas Hain, Stefan Goetze, Jon Barker:
Using Speech Foundational Models in Loss Functions for Hearing Aid Speech Enhancement. CoRR abs/2407.13333 (2024) - [i44]Olga Iakovenko, Thomas Hain:
Methods for Automatic Matrix Language Determination of Code-Switched Speech. CoRR abs/2410.02521 (2024) - 2023
- [c162]Muhammad Umar Farooq, Rehan Ahmad, Thomas Hain:
MUST: A Multilingual Student-Teacher Learning Approach for Low-Resource Speech Recognition. ASRU 2023: 1-6 - [c161]Elaf Islam, Thomas Hain, Protima Nomo Sudro:
Simulation of Teacher-Learner Interaction in English Language Pronunciation Learning. ASRU 2023: 1-6 - [c160]Amit Meghanani, Thomas Hain:
Deriving Translational Acoustic Sub-Word Embeddings. ASRU 2023: 1-8 - [c159]William Ravenscroft, Stefan Goetze, Thomas Hain:
On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments. ASRU 2023: 1-7 - [c158]Protima Nomo Sudro, Anton Ragni, Thomas Hain:
Adapting Pretrained Models for Adult to Child Voice Conversion. EUSIPCO 2023: 271-275 - [c157]William Ravenscroft, Stefan Goetze, Thomas Hain:
On Data Sampling Strategies for Training Neural Network Speech Separation Models. EUSIPCO 2023: 331-335 - [c156]Anna Ollerenshaw, Md Asif Jalal, Thomas Hain:
Probing Statistical Representations for End-to-End ASR. EUSIPCO 2023: 401-405 - [c155]Rehan Ahmad, Md Asif Jalal, Muhammad Umar Farooq, Anna Ollerenshaw, Thomas Hain:
Towards Domain Generalisation in ASR with Elitist Sampling and Ensemble Knowledge Distillation. ICASSP 2023: 1-5 - [c154]George Close, William Ravenscroft, Thomas Hain, Stefan Goetze:
Perceive and Predict: Self-Supervised Speech Representation Based Loss Functions for Speech Enhancement. ICASSP 2023: 1-5 - [c153]William Ravenscroft, Stefan Goetze, Thomas Hain:
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation. ICASSP 2023: 1-5 - [c152]Cong-Thanh Do, Rama Doddipatla, Mohan Li, Thomas Hain:
Domain Adaptive Self-supervised Training of Automatic Speech Recognition. INTERSPEECH 2023: 4389-4393 - [c151]Muhammad Umar Farooq, Thomas Hain:
Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition. INTERSPEECH 2023: 5072-5076 - [c150]Elaf Islam, Chanho Park, Thomas Hain:
Exploring Speech Representations for Proficiency Assessment in Language Learning. SLaTE 2023: 151-155 - [c149]George Close, Thomas Hain, Stefan Goetze:
The Effect of Spoken Language on Speech Enhancement Using Self-Supervised Speech Representation Loss Functions. WASPAA 2023: 1-5 - [i43]George Close, William Ravenscroft, Thomas Hain, Stefan Goetze:
Perceive and predict: self-supervised speech representation based loss functions for speech enhancement. CoRR abs/2301.04388 (2023) - [i42]Rehan Ahmad, Md Asif Jalal, Muhammad Umar Farooq, Anna Ollerenshaw, Thomas Hain:
Towards domain generalisation in ASR with elitist sampling and ensemble knowledge distillation. CoRR abs/2303.00550 (2023) - [i41]William Ravenscroft, Stefan Goetze, Thomas Hain:
On Data Sampling Strategies for Training Neural Network Speech Separation Models. CoRR abs/2304.07142 (2023) - [i40]Muhammad Umar Farooq, Thomas Hain:
Learning Cross-lingual Mappings for Data Augmentation to Improve Low-Resource Speech Recognition. CoRR abs/2306.08577 (2023) - [i39]Anna Ollerenshaw, Md Asif Jalal, Rosanna Milner, Thomas Hain:
Empirical Interpretation of the Relationship Between Speech Acoustic Context and Emotion Recognition. CoRR abs/2306.17500 (2023) - [i38]George Close, Thomas Hain, Stefan Goetze:
Non Intrusive Intelligibility Predictor for Hearing Impaired Individuals using Self Supervised Speech Representations. CoRR abs/2307.13423 (2023) - [i37]George Close, Thomas Hain, Stefan Goetze:
The Effect of Spoken Language on Speech Enhancement using Self-Supervised Speech Representation Loss Functions. CoRR abs/2307.14502 (2023) - [i36]William Ravenscroft, Stefan Goetze, Thomas Hain:
On Time Domain Conformer Models for Monaural Speech Separation in Noisy Reverberant Acoustic Environments. CoRR abs/2310.06125 (2023) - [i35]Chanho Park, Chengsong Lu, Mingjie Chen, Thomas Hain:
Fast Word Error Rate Estimation Using Self-Supervised Representations For Speech And Text. CoRR abs/2310.08225 (2023) - [i34]Muhammad Umar Farooq, Rehan Ahmad, Thomas Hain:
MUST: A Multilingual Student-Teacher Learning approach for low-resource speech recognition. CoRR abs/2310.18865 (2023) - [i33]George Close, William Ravenscroft, Thomas Hain, Stefan Goetze:
Multi-CMGAN+/+: Leveraging Multi-Objective Speech Quality Metric Prediction for Speech Enhancement. CoRR abs/2312.08979 (2023) - 2022
- [j16]Madina Hasan, Nicholas Jefferson, Thomas Hain, Jeremy Dawson:
Automatic detection of behavioural codes in team interactions. Comput. Speech Lang. 74: 101339 (2022) - [c148]William Ravenscroft, Stefan Goetze, Thomas Hain:
Receptive Field Analysis of Temporal Convolutional Networks for Monaural Speech Dereverberation. EUSIPCO 2022: 80-84 - [c147]George Close, Thomas Hain, Stefan Goetze:
MetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen Data. EUSIPCO 2022: 165-169 - [c146]Anna Ollerenshaw, Md Asif Jalal, Thomas Hain:
Insights of Neural Representations in Multi-Banded and Multi-Channel Convolutional Transformers for End-to-End ASR. EUSIPCO 2022: 434-438 - [c145]Jose Antonio Lopez Saenz, Thomas Hain:
A Model for Assessor Bias in Automatic Pronunciation Assessment. ICASSP 2022: 7267-7271 - [c144]Chanho Park, Rehan Ahmad, Thomas Hain:
Unsupervised Data Selection for Speech Recognition with Contrastive Loss Ratios. ICASSP 2022: 8587-8591 - [c143]George Close, Samuel Hollands, Stefan Goetze, Thomas Hain:
Non-intrusive Speech Intelligibility Metric Prediction for Hearing Impaired Individuals. INTERSPEECH 2022: 3483-3487 - [c142]Muhammad Umar Farooq, Thomas Hain:
Investigating the Impact of Crosslingual Acoustic-Phonetic Similarities on Multilingual Speech Recognition. INTERSPEECH 2022: 3849-3853 - [c141]Muhammad Umar Farooq, Darshan Adiga Haniya Narayana, Thomas Hain:
Non-Linear Pairwise Language Mappings for Low-Resource Multilingual Acoustic Model Fusion. INTERSPEECH 2022: 4850-4854 - [c140]William Ravenscroft, Stefan Goetze, Thomas Hain:
Utterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberation. IWAENC 2022: 1-5 - [i32]George Close, Thomas Hain, Stefan Goetze:
MetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen Data. CoRR abs/2203.12369 (2022) - [i31]William Ravenscroft, Stefan Goetze, Thomas Hain:
Receptive Field Analysis of Temporal Convolutional Networks for Monaural Speech Dereverberation. CoRR abs/2204.06439 (2022) - [i30]William Ravenscroft, Stefan Goetze, Thomas Hain:
Utterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberation. CoRR abs/2205.08455 (2022) - [i29]Anna Ollerenshaw, Md Asif Jalal, Thomas Hain:
Insights on Neural Representations for End-to-End Speech Recognition. CoRR abs/2205.09456 (2022) - [i28]Rosanna Milner, Md Asif Jalal, Raymond W. M. Ng, Thomas Hain:
A cross-corpus study on speech emotion recognition. CoRR abs/2207.02104 (2022) - [i27]Muhammad Umar Farooq, Thomas Hain:
Investigating the Impact of Cross-lingual Acoustic-Phonetic Similarities on Multilingual Speech Recognition. CoRR abs/2207.03390 (2022) - [i26]Muhammad Umar Farooq, Darshan Adiga Haniya Narayana, Thomas Hain:
Non-Linear Pairwise Language Mappings for Low-Resource Multilingual Acoustic Model Fusion. CoRR abs/2207.03391 (2022) - [i25]Chanho Park, Rehan Ahmad, Thomas Hain:
Unsupervised data selection for Speech Recognition with contrastive loss ratios. CoRR abs/2207.12028 (2022) - [i24]William Ravenscroft, Stefan Goetze, Thomas Hain:
Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech Separation. CoRR abs/2210.15305 (2022) - [i23]Anna Ollerenshaw, Md Asif Jalal, Thomas Hain:
Probing Statistical Representations For End-To-End ASR. CoRR abs/2211.01993 (2022) - [i22]Anna Ollerenshaw, Md Asif Jalal, Thomas Hain:
Dynamic Kernels and Channel Attention with Multi-Layer Embedding Aggregation for Speaker Verification. CoRR abs/2211.02000 (2022) - 2021
- [j15]Asmaa El Hannani, Rahhal Errattahi, Fatima Zahra Salmam, Thomas Hain, Hassan Ouahmane:
Evaluation of the effectiveness and efficiency of state-of-the-art features and models for automatic speech recognition error detection. J. Big Data 8(1): 5 (2021) - [j14]Yanpei Shi, Qiang Huang, Thomas Hain:
H-VECTORS: Improving the robustness in utterance-level speaker embeddings using a hierarchical attention model. Neural Networks 142: 329-339 (2021) - [c139]Korbinian Friedl, Georgios Rizos, Lukas Stappen, Madina Hasan, Lucia Specia, Thomas Hain, Björn W. Schuller:
Uncertainty Aware Review Hallucination for Science Article Classification. ACL/IJCNLP (Findings) 2021: 5004-5009 - [c138]Jose Antonio Lopez Saenz, Md Asif Jalal, Rosanna Milner, Thomas Hain:
Attention Based Model for Segmental Pronunciation Error Detection. ASRU 2021: 725-732 - [c137]Mingjie Chen, Yanpei Shi, Thomas Hain:
Towards Low-Resource Stargan Voice Conversion Using Weight Adaptive Instance Normalization. ICASSP 2021: 5949-5953 - [c136]Qiang Huang, Thomas Hain:
Improving Audio Anomalies Recognition Using Temporal Convolutional Attention Networks. ICASSP 2021: 6473-6477 - [c135]Cong-Thanh Do, Rama Doddipatla, Thomas Hain:
Multiple-Hypothesis CTC-Based Semi-Supervised Adaptation of End-to-End Speech Recognition. ICASSP 2021: 6978-6982 - [c134]Anna Ollerenshaw, Md. Asif Jalal, Thomas Hain:
Insights on Neural Representations for End-to-End Speech Recognition. Interspeech 2021: 4079-4083 - [c133]Shengjie Huang, Mingjie Chen, Yanyan Xu, Dengfeng Ke, Thomas Hain:
WINVC: One-Shot Voice Conversion with Weight Adaptive Instance Normalization. PRICAI (2) 2021: 559-573 - [c132]Jose Antonio Lopez Saenz, Thomas Hain:
Use of Speaker Metadata for Improving Automatic Pronunciation Assessment. SLSP 2021: 61-72 - [c131]Yanpei Shi, Thomas Hain:
Contextual Joint Factor Acoustic Embeddings. SLT 2021: 750-757 - [c130]Yanpei Shi, Thomas Hain:
Supervised Speaker Embedding De-Mixing in Two-Speaker Environment. SLT 2021: 758-765 - [i21]Cong-Thanh Do, Rama Doddipatla, Thomas Hain:
Multiple-hypothesis CTC-based semi-supervised adaptation of end-to-end speech recognition. CoRR abs/2103.15515 (2021) - 2020
- [c129]Cong-Thanh Do, Shucong Zhang, Thomas Hain:
Selective Adaptation of End-to-End Speech Recognition using Hybrid CTC/Attention Architecture for Noise Robustness. EUSIPCO 2020: 321-325 - [c128]Yanpei Shi, Qiang Huang, Thomas Hain:
H-Vectors: Utterance-Level Speaker Embedding Using a Hierarchical Attention Model. ICASSP 2020: 7579-7583 - [c127]Yanpei Shi, Qiang Huang, Thomas Hain:
Speaker Re-Identification with Speaker Dependent Speech Enhancement. INTERSPEECH 2020: 1530-1534 - [c126]Lukas Stappen, Georgios Rizos, Madina Hasan, Thomas Hain, Björn W. Schuller:
Uncertainty-Aware Machine Support for Paper Reviewing on the Interspeech 2019 Submission Corpus. INTERSPEECH 2020: 1808-1812 - [c125]Yanpei Shi, Qiang Huang, Thomas Hain:
Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification. INTERSPEECH 2020: 2992-2996 - [c124]Md Asif Jalal, Rosanna Milner, Thomas Hain, Roger K. Moore:
Removing Bias with Residual Mixture of Multi-View Attention for Speech Emotion Recognition. INTERSPEECH 2020: 4084-4088 - [c123]Md. Asif Jalal, Rosanna Milner, Thomas Hain:
Empirical Interpretation of Speech Emotion Perception with Attention Based Model for Speech Emotion Recognition. INTERSPEECH 2020: 4113-4117 - [c122]Qiang Huang, Thomas Hain:
Exploration of Audio Quality Assessment and Anomaly Localisation Using Attention Models. INTERSPEECH 2020: 4611-4615 - [c121]Hardik B. Sailor, Thomas Hain:
Multilingual Speech Recognition Using Language-Specific Phoneme Recognition as Auxiliary Task for Indian Languages. INTERSPEECH 2020: 4756-4760 - [c120]Mingjie Chen, Thomas Hain:
Unsupervised Acoustic Unit Representation Learning for Voice Conversion Using WaveNet Auto-Encoders. INTERSPEECH 2020: 4866-4870 - [c119]Yanpei Shi, Qiang Huang, Thomas Hain:
Robust Speaker Recognition Using Speech Enhancement And Attention Model. Odyssey 2020: 451-458 - [i20]Yanpei Shi, Qiang Huang, Thomas Hain:
Robust Speaker Recognition Using Speech Enhancement And Attention Model. CoRR abs/2001.05031 (2020) - [i19]Yanpei Shi, Thomas Hain:
Supervised Speaker Embedding De-Mixing in Two-Speaker Environment. CoRR abs/2001.06397 (2020) - [i18]Yanpei Shi, Qiang Huang, Thomas Hain:
Weakly Supervised Training of Hierarchical Attention Networks for Speaker Identification. CoRR abs/2005.07817 (2020) - [i17]Yanpei Shi, Qiang Huang, Thomas Hain:
Speaker Re-identification with Speaker Dependent Speech Enhancement. CoRR abs/2005.07818 (2020) - [i16]Qiang Huang, Thomas Hain:
Exploration of Audio Quality Assessment and Anomaly Localisation Using Attention Models. CoRR abs/2005.08053 (2020) - [i15]Mingjie Chen, Thomas Hain:
Unsupervised Acoustic Unit Representation Learning for Voice Conversion using WaveNet Auto-encoders. CoRR abs/2008.06892 (2020) - [i14]Qiang Huang, Thomas Hain:
Improving Audio Anomalies Recognition Using Temporal Convolutional Attention Network. CoRR abs/2010.11286 (2020) - [i13]Mingjie Chen, Yanpei Shi, Thomas Hain:
Towards Low-Resource StarGAN Voice Conversion using Weight Adaptive Instance Normalization. CoRR abs/2010.11646 (2020) - [i12]Yanpei Shi, Mingjie Chen, Qiang Huang, Thomas Hain:
T-vectors: Weakly Supervised Speaker Identification Using Hierarchical Transformer Model. CoRR abs/2010.16071 (2020)
2010 – 2019
- 2019
- [j13]Rahhal Errattahi, Asmaa El Hannani, Thomas Hain, Hassan Ouahmane:
System-independent ASR error detection and classification using Recurrent Neural Network. Comput. Speech Lang. 55: 187-199 (2019) - [j12]Salil Deena, Madina Hasan, Mortaza Doulaty, Oscar Saz, Thomas Hain:
Recurrent Neural Network Language Model Adaptation for Multi-Genre Broadcast Speech Recognition and Alignment. IEEE ACM Trans. Audio Speech Lang. Process. 27(3): 572-582 (2019) - [c118]Rosanna Milner, Md Asif Jalal, Raymond W. M. Ng, Thomas Hain:
A Cross-Corpus Study on Speech Emotion Recognition. ASRU 2019: 304-311 - [c117]Md Asif Jalal, Roger K. Moore, Thomas Hain:
Spatio-Temporal Context Modelling for Speech Emotion Classification. ASRU 2019: 853-859 - [c116]Hardik B. Sailor, Salil Deena, Md Asif Jalal, Rasa Lileikyte, Thomas Hain:
Unsupervised Adaptation of Acoustic Models for ASR Using Utterance-Level Embeddings from Squeeze and Excitation Networks. ASRU 2019: 980-987 - [c115]Qiang Huang, Thomas Hain:
Detecting Mismatch Between Speech and Transcription Using Cross-Modal Attention. INTERSPEECH 2019: 584-588 - [c114]Md Asif Jalal, Erfan Loweimi, Roger K. Moore, Thomas Hain:
Learning Temporal Clusters Using Capsule Routing for Speech Emotion Recognition. INTERSPEECH 2019: 1701-1705 - [c113]Mortaza Doulaty, Thomas Hain:
Latent Dirichlet Allocation Based Acoustic Data Selection for Automatic Speech Recognition. INTERSPEECH 2019: 3228-3232 - [i11]Mortaza Doulaty, Thomas Hain:
Latent Dirichlet Allocation Based Acoustic Data Selection for Automatic Speech Recognition. CoRR abs/1907.01302 (2019) - [i10]Yanpei Shi, Qiang Huang, Thomas Hain:
Improving Robustness In Speaker Identification Using A Two-Stage Attention Model. CoRR abs/1909.11200 (2019) - [i9]Yanpei Shi, Qiang Huang, Thomas Hain:
Contextual Joint Factor Acoustic Embeddings. CoRR abs/1910.07601 (2019) - [i8]Yanpei Shi, Qiang Huang, Thomas Hain:
H-VECTORS: Utterance-level Speaker Embedding Using A Hierarchical Attention Model. CoRR abs/1910.07900 (2019) - 2018
- [j11]Oscar Saz, Salil Deena, Mortaza Doulaty, Madina Hasan, Bilal Khaliq, Rosanna Milner, Raymond W. M. Ng, Julia Olcoz, Thomas Hain:
Lightly supervised alignment of subtitles on multi-genre broadcasts. Multim. Tools Appl. 77(23): 30533-30550 (2018) - [c112]Rahhal Errattahi, Asmaa El Hannani, Thomas Hain, Hassan Ouahmane:
Towards a generic approach for automatic speech recognition error detection and classification. ATSIP 2018: 1-6 - [c111]Erfan Loweimi, Jon Barker, Thomas Hain:
Exploring the Use of Group Delay for Generalised VTS Based Noise Compensation. ICASSP 2018: 4824-4828 - [c110]Erfan Loweimi, Jon Barker, Thomas Hain:
On the Usefulness of the Speech Phase Spectrum for Pitch Extraction. INTERSPEECH 2018: 696-700 - [c109]Mauro Nicolao, Michiel Sanders, Thomas Hain:
Improved Acoustic Modelling for Automatic Literacy Assessment of Children. INTERSPEECH 2018: 1666-1670 - [c108]Rahhal Errattahi, Salil Deena, Asmaa El Hannani, Hassan Ouahmane, Thomas Hain:
Improving ASR Error Detection with RNNLM Adaptation. SLT 2018: 190-196 - 2017
- [j10]Oscar Saz, Thomas Hain:
Acoustic adaptation to dynamic background conditions with asynchronous transformations. Comput. Speech Lang. 41: 180-194 (2017) - [j9]Raymond W. M. Ng, Mauro Nicolao, Thomas Hain:
Unsupervised crosslingual adaptation of tokenisers for spoken language recognition. Comput. Speech Lang. 46: 327-342 (2017) - [c107]Salil Deena, Raymond W. M. Ng, Pranava Swaroop Madhyastha, Lucia Specia, Thomas Hain:
Exploring the use of acoustic embeddings in neural machine translation. ASRU 2017: 450-457 - [c106]Rosanna Milner, Thomas Hain:
DNN approach to speaker diarisation using speaker channels. ICASSP 2017: 4925-4929 - [c105]Erfan Loweimi, Jon Barker, Thomas Hain:
Statistical normalisation of phase-based feature representation for robust speech recognition. ICASSP 2017: 5310-5314 - [c104]Raymond W. M. Ng, Alvin C. M. Kwan, Tan Lee, Thomas Hain:
Shefce: A Cantonese-English bilingual speech corpus for pronunciation assessment. ICASSP 2017: 5825-5829 - [c103]Erfan Loweimi, Jon Barker, Oscar Saz-Torralba, Thomas Hain:
Robust Source-Filter Separation of Speech Signal in the Phase Domain. INTERSPEECH 2017: 414-418 - [c102]Erfan Loweimi, Jon Barker, Thomas Hain:
Channel Compensation in the Generalised Vector Taylor Series Approach to Robust ASR. INTERSPEECH 2017: 2466-2470 - [c101]Salil Deena, Raymond W. M. Ng, Pranava Swaroop Madhyastha, Lucia Specia, Thomas Hain:
Semi-Supervised Adaptation of RNNLMs by Fine-Tuning with Domain-Specific Auxiliary Features. INTERSPEECH 2017: 2715-2719 - [c100]Chenhao Wu, Raymond W. M. Ng, Oscar Saz-Torralba, Thomas Hain:
Analysing acoustic model changes for active learning in automatic speech recognition. IWSSIP 2017: 1-5 - 2016
- [c99]Rahhal Errattahi, Asmaa El Hannani, Hassan Ouahmane, Thomas Hain:
Automatic speech recognition errors detection using supervised learning techniques. AICCSA 2016: 1-6 - [c98]Rosanna Milner, Thomas Hain:
Segment-oriented evaluation of speaker diarisation performance. ICASSP 2016: 5460-5464 - [c97]Raymond W. M. Ng, Kashif Shah, Lucia Specia, Thomas Hain:
Groupwise learning for ASR k-best list reranking in spoken language translation. ICASSP 2016: 6120-6124 - [c96]Sarah Al-Shareef, Thomas Hain:
Colloquialising Modern Standard Arabic Text for Improved Speech Recognition. INTERSPEECH 2016: 1345-1349 - [c95]Thomas Hain, Jeremy Christian, Oscar Saz, Salil Deena, Madina Hasan, Raymond W. M. Ng, Rosanna Milner, Mortaza Doulaty, Yulan Liu:
webASR 2 - Improved Cloud Based Speech Technology. INTERSPEECH 2016: 1613-1617 - [c94]Julia Olcoz, Oscar Saz, Thomas Hain:
Error Correction in Lightly Supervised Alignment of Broadcast Subtitles. INTERSPEECH 2016: 2110-2114 - [c93]Mortaza Doulaty, Oscar Saz, Raymond W. M. Ng, Thomas Hain:
Automatic Genre and Show Identification of Broadcast Media. INTERSPEECH 2016: 2115-2119 - [c92]Rosanna Milner, Thomas Hain:
DNN-Based Speaker Clustering for Speaker Diarisation. INTERSPEECH 2016: 2185-2189 - [c91]Salil Deena, Madina Hasan, Mortaza Doulaty, Oscar Saz, Thomas Hain:
Combining Feature and Model-Based Adaptation of RNNLMs for Multi-Genre Broadcast Speech Recognition. INTERSPEECH 2016: 2343-2347 - [c90]Iñigo Casanueva, Thomas Hain, Phil D. Green:
Improving Generalisation to New Speakers in Spoken Dialogue State Tracking. INTERSPEECH 2016: 2726-2730 - [c89]Raymond W. M. Ng, Bhusan Chettri, Thomas Hain:
Combining Weak Tokenisers for Phonotactic Language Recognition in a Resource-Constrained Setting. INTERSPEECH 2016: 2939-2943 - [c88]Erfan Loweimi, Jon Barker, Thomas Hain:
Use of Generalised Nonlinearity in Vector Taylor Series Noise Compensation for Robust Speech Recognition. INTERSPEECH 2016: 3798-3802 - [c87]Yulan Liu, Charles Fox, Madina Hasan, Thomas Hain:
The Sheffield Wargame Corpus - Day Two and Day Three. INTERSPEECH 2016: 3833-3837 - [c86]Ghada AlHarbi, Thomas Hain:
The OpenCourseWare Metadiscourse (OCWMD) Corpus. LREC 2016 - [c85]Mauro Nicolao, Heidi Christensen, Stuart P. Cunningham, Phil D. Green, Thomas Hain:
A Framework for Collecting Realistic Recordings of Dysarthric Speech - the homeService Corpus. LREC 2016 - [c84]Raymond W. M. Ng, Mauro Nicolao, Oscar Saz, Madina Hasan, Bhusan Chettri, Mortaza Doulaty, Tan Lee, Thomas Hain:
The Sheffield language recognition system in NIST LRE 2015. Odyssey 2016: 181-187 - [c83]Iñigo Casanueva, Thomas Hain, Mauro Nicolao, Phil D. Green:
Using phone features to improve dialogue state tracking generalisation to unseen states. SIGDIAL Conference 2016: 80-89 - [i7]Mortaza Doulaty, Oscar Saz, Raymond W. M. Ng, Thomas Hain:
Automatic Genre and Show Identification of Broadcast Media. CoRR abs/1606.03333 (2016) - 2015
- [c82]Mortaza Doulaty, Oscar Saz, Raymond W. M. Ng, Thomas Hain:
Latent Dirichlet Allocation based organisation of broadcast media archives for deep neural network adaptation. ASRU 2015: 130-136 - [c81]Oscar Saz, Mortaza Doulaty, Salil Deena, Rosanna Milner, Raymond W. M. Ng, Madina Hasan, Yulan Liu, Thomas Hain:
The 2015 sheffield system for transcription of Multi-Genre Broadcast media. ASRU 2015: 624-631 - [c80]Rosanna Milner, Oscar Saz, Salil Deena, Mortaza Doulaty, Raymond W. M. Ng, Thomas Hain:
The 2015 sheffield system for longitudinal diarisation of broadcast media. ASRU 2015: 632-638 - [c79]Peter Bell, Mark J. F. Gales, Thomas Hain, Jonathan Kilgour, Pierre Lanchantin, Xunying Liu, Andrew McParland, Steve Renals, Oscar Saz, Mirjam Wester, Philip C. Woodland:
The MGB challenge: Evaluating multi-genre broadcast media recognition. ASRU 2015: 687-693 - [c78]Ghada AlHarbi, Thomas Hain:
Using Topic Segmentation Models for the Automatic Organisation of MOOCs resources. EDM 2015: 524-527 - [c77]Yulan Liu, Penny Karanasou, Thomas Hain:
An investigation into speaker informed DNN front-end for LVCSR. ICASSP 2015: 4300-4304 - [c76]Raymond W. M. Ng, Kashif Shah, Wilker Aziz, Lucia Specia, Thomas Hain:
Quality estimation for asr k-best list rescoring in spoken language translation. ICASSP 2015: 5226-5230 - [c75]Mauro Nicolao, Amy V. Beeston, Thomas Hain:
Automatic assessment of English learner pronunciation using discriminative classifiers. ICASSP 2015: 5351-5355 - [c74]Madina Hasan, Rama Doddipatla, Thomas Hain:
Noise-matched training of CRF based sentence end detection models. INTERSPEECH 2015: 349-353 - [c73]Erfan Loweimi, Jon Barker, Thomas Hain:
Source-filter separation of speech signal in the phase domain. INTERSPEECH 2015: 598-602 - [c72]Raymond W. M. Ng, Kashif Shah, Lucia Specia, Thomas Hain:
A study on the stability and effectiveness of features in quality estimation for spoken language translation. INTERSPEECH 2015: 2257-2261 - [c71]Mortaza Doulaty, Oscar Saz, Thomas Hain:
Data-selective transfer learning for multi-domain speech recognition. INTERSPEECH 2015: 2897-2901 - [c70]Mortaza Doulaty, Oscar Saz, Thomas Hain:
Unsupervised domain discovery using latent dirichlet allocation for acoustic modelling in speech recognition. INTERSPEECH 2015: 3640-3644 - [c69]Iñigo Casanueva, Thomas Hain, Heidi Christensen, Ricard Marxer, Phil D. Green:
Knowledge transfer between speakers for personalised dialogue management. SIGDIAL Conference 2015: 12-21 - [c68]Erfan Loweimi, Mortaza Doulaty, Jon Barker, Thomas Hain:
Long-Term Statistical Feature Extraction from Speech Signal and Its Application in Emotion Recognition. SLSP 2015: 173-184 - [c67]Ghada AlHarbi, Raymond W. M. Ng, Thomas Hain:
Annotating meta-discourse in academic lectures from different disciplines. SLaTE 2015: 161-166 - [i6]Mortaza Doulaty, Oscar Saz, Thomas Hain:
Data-selective Transfer Learning for Multi-Domain Speech Recognition. CoRR abs/1509.02409 (2015) - [i5]Mortaza Doulaty, Oscar Saz, Thomas Hain:
Unsupervised Domain Discovery using Latent Dirichlet Allocation for Acoustic Modelling in Speech Recognition. CoRR abs/1509.02412 (2015) - [i4]Raymond W. M. Ng, Mortaza Doulaty, Rama Doddipatla, Wilker Aziz, Kashif Shah, Oscar Saz, Madina Hasan, Ghada AlHarbi, Lucia Specia, Thomas Hain:
The USFD Spoken Language Translation System for IWSLT 2014. CoRR abs/1509.03870 (2015) - [i3]Oscar Saz, Mortaza Doulaty, Thomas Hain:
Background-tracking Acoustic Features for Genre Identification of Broadcast Shows. CoRR abs/1509.04934 (2015) - [i2]Mortaza Doulaty, Oscar Saz, Raymond W. M. Ng, Thomas Hain:
Latent Dirichlet Allocation Based Organisation of Broadcast Media Archives for Deep Neural Network Adaptation. CoRR abs/1511.05076 (2015) - [i1]Oscar Saz, Mortaza Doulaty, Salil Deena, Rosanna Milner, Raymond W. M. Ng, Madina Hasan, Yulan Liu, Thomas Hain:
The 2015 Sheffield System for Transcription of Multi-Genre Broadcast Media. CoRR abs/1512.06643 (2015) - 2014
- [j8]Herman Kamper, Febe de Wet, Thomas Hain, Thomas Niesler:
Capitalising on North American speech resources for the development of a South African English large vocabulary speech recognition system. Comput. Speech Lang. 28(6): 1255-1268 (2014) - [c66]Yulan Liu, Pengyuan Zhang, Thomas Hain:
Using neural network front-ends on far field multiple microphones based speech recognition. ICASSP 2014: 5542-5546 - [c65]Oscar Saz, Thomas Hain:
Using contextual information in joint factor eigenspace MLLR for speech recognition in diverse scenarios. ICASSP 2014: 6314-6318 - [c64]I. Casanueva, Heidi Christensen, Thomas Hain, Phil D. Green:
Adaptive speech recognition and dialogue management for users with speech disorders. INTERSPEECH 2014: 1033-1037 - [c63]Rama Doddipatla, Madina Hasan, Thomas Hain:
Speaker dependent bottleneck layer training for speaker adaptation in automatic speech recognition. INTERSPEECH 2014: 2199-2203 - [c62]Charles Fox, Thomas Hain:
Extending Limabeam with discrimination and coarse gradients. INTERSPEECH 2014: 2440-2444 - [c61]Madina Hasan, Rama Doddipatla, Thomas Hain:
Multi-pass sentence-end detection of lecture speech. INTERSPEECH 2014: 2902-2906 - [c60]Raymond W. M. Ng, Mortaza Doulaty, Rama Doddipatla, Wilker Aziz, Kashif Shah, Oscar Saz, Madina Hasan, Ghada AlHaribi, Lucia Specia, Thomas Hain:
The USFD SLT system for IWSLT 2014. IWSLT (Evaluation Campaign) 2014 - [c59]Oscar Saz, Mortaza Doulaty, Thomas Hain:
Background-tracking acoustic features for genre identification of broadcast shows. SLT 2014: 118-123 - [c58]Pengyuan Zhang, Yulan Liu, Thomas Hain:
Semi-supervised DNN training in meeting recognition. SLT 2014: 141-146 - [c57]Heidi Christensen, I. Casanueva, Stuart P. Cunningham, Phil D. Green, Thomas Hain:
Automatic selection of speakers for improved acoustic modelling: recognition of disordered speech with sparse data. SLT 2014: 254-259 - 2013
- [c56]Charles Fox, Thomas Hain:
Lightly supervised learning from a damaged natural speech corpus. ICASSP 2013: 8086-8090 - [c55]Raymond W. M. Ng, Thomas Hain, Trevor Cohn:
Adaptation of lecture speech recognition system with machine translation output. ICASSP 2013: 8401-8405 - [c54]Pierre Lanchantin, Peter Bell, Mark J. F. Gales, Thomas Hain, Xunying Liu, Yanhua Long, Jennifer Quinnell, Steve Renals, Oscar Saz, Matthew Stephen Seigel, Pawel Swietojanski, Philip C. Woodland:
Automatic Transcription of Multi-genre Media Archives. SLAM@INTERSPEECH 2013: 26-31 - [c53]Charles Fox, Yulan Liu, Erich Zwyssig, Thomas Hain:
The sheffield wargames corpus. INTERSPEECH 2013: 1116-1120 - [c52]Heidi Christensen, Phil D. Green, Thomas Hain:
Learning speaker-specific pronunciations of disordered speech. INTERSPEECH 2013: 1159-1163 - [c51]Oscar Saz, Thomas Hain:
Asynchronous factorisation of speaker and background with feature transforms in speech recognition. INTERSPEECH 2013: 1238-1242 - [c50]Heidi Christensen, Magda B. Aniol, Peter Bell, Phil D. Green, Thomas Hain, Simon King, Pawel Swietojanski:
Combining in-domain and out-of-domain speech data for automatic recognition of disordered speech. INTERSPEECH 2013: 3642-3645 - [c49]Heidi Christensen, Iñigo Casanueva, Stuart P. Cunningham, Phil D. Green, Thomas Hain:
homeService: Voice-enabled assistive technology in the home using cloud-based automatic speech recognition. SLPAT 2013: 29-34 - 2012
- [j7]Thomas Hain, Lukás Burget, John Dines, Philip N. Garner, Frantisek Grézl, Asmaa El Hannani, Marijn Huijbregts, Martin Karafiát, Mike Lincoln, Vincent Wan:
Transcribing Meetings With the AMIDA Systems. IEEE Trans. Speech Audio Process. 20(2): 486-498 (2012) - [j6]Matthew Gibson, Thomas Hain:
Correctness-Adjusted Unsupervised Discriminative Acoustic Model Adaptation. IEEE Trans. Speech Audio Process. 20(10): 2648-2656 (2012) - [c48]Matthew Gibson, Thomas Hain:
Application of SVM-based correctness predictions to unsupervised discriminative speaker adaptation. ICASSP 2012: 4341-4344 - [c47]Gwénolé Lecorvé, John Dines, Thomas Hain, Petr Motlícek:
Supervised and unsupervised Web-based language model domain adaptation. INTERSPEECH 2012: 182-185 - [c46]Raymond W. M. Ng, Thomas Hain, Keikichi Hirose:
An alignment matching method to explore pseudosyllable properties across different corpora. INTERSPEECH 2012: 863-866 - [c45]Heidi Christensen, Stuart P. Cunningham, Charles Fox, Phil D. Green, Thomas Hain:
A comparative study of adaptive, automatic recognition of disordered speech. INTERSPEECH 2012: 1776-1779 - [c44]Sarah Al-Shareef, Thomas Hain:
CRF-based Diacritisation of Colloquial Arabic for Automatic Speech Recognition. INTERSPEECH 2012: 1824-1827 - [c43]Ghada AlHarbi, Thomas Hain:
Automatic transcription of academic lectures from diverse disciplines. SLT 2012: 398-403 - [c42]Herman Kamper, Febe de Wet, Thomas Hain, Thomas Niesler:
Resource development and experiments in automatic south african broadcast news transcription. SLTU 2012: 102-106 - [c41]Gwénolé Lecorvé, John Dines, Thomas Hain, Petr Motlícek:
Impact du degré de supervision sur l'adaptation à un domaine d'un modèle de langage à partir du Web (Impact of the level of supervision on Web-based language model domain adaptation) [in French]. JEP-TALN-RECITAL 2012 2012: 193-200 - 2011
- [c40]Davide Marino, Thomas Hain:
An Analysis of Automatic Speech Recognition with Multiple Microphones. INTERSPEECH 2011: 1281-1284 - [c39]Sarah Al-Shareef, Thomas Hain:
An Investigation in Speech Recognition for Colloquial Arabic. INTERSPEECH 2011: 2869-2872 - [c38]Timothy Kempton, Roger K. Moore, Thomas Hain:
Cross-Language Phone Recognition when the Target Language Phoneme Inventory is not Known. INTERSPEECH 2011: 3165-3168 - [c37]Stuart N. Wrigley, Thomas Hain:
Web-Based Automatic Speech Recognition Service - webASR. INTERSPEECH 2011: 3265-3268 - [c36]Stuart N. Wrigley, Thomas Hain:
Making an Automatic Speech Recognition Service Freely Available on the Web. INTERSPEECH 2011: 3325-3326 - [c35]Roger C. F. Tucker, Dan Fry, Vincent Wan, Stuart N. Wrigley, Thomas Hain:
Extending Audio Notetaker to Browse WebASR Transcriptions. INTERSPEECH 2011: 3329-3330 - 2010
- [j5]Asmaa El Hannani, Thomas Hain:
Automatic Optimization of Speech Decoder Parameters. IEEE Signal Process. Lett. 17(1): 95-98 (2010) - [j4]Matt Gibson, Thomas Hain:
Error Approximation and Minimum Phone Error Acoustic Model Estimation. IEEE Trans. Speech Audio Process. 18(6): 1269-1279 (2010) - [c34]Thomas Hain, Lukás Burget, John Dines, Philip N. Garner, Asmaa El Hannani, Marijn Huijbregts, Martin Karafiát, Mike Lincoln, Vincent Wan:
The AMIDA 2009 meeting transcription system. INTERSPEECH 2010: 358-361
2000 – 2009
- 2009
- [c33]Philip N. Garner, John Dines, Thomas Hain, Asmaa El Hannani, Martin Karafiát, Danil Korchagin, Mike Lincoln, Vincent Wan, Le Zhang:
Real-time ASR from meetings. INTERSPEECH 2009: 2119-2122 - 2008
- [c32]Thomas Hain, Asmaa El Hannani, Stuart N. Wrigley, Vincent Wan:
Automatic speech recognition for scientific purposes - webASR. INTERSPEECH 2008: 504-507 - [c31]Martin Karafiát, Lukás Burget, Thomas Hain, Jan Cernocký:
Discrimininative training of narrow band - wide band adapted systems for meeting recognition. INTERSPEECH 2008: 1217-1220 - [c30]Vincent Wan, John Dines, Asmaa El Hannani, Thomas Hain:
Bob: A lexicon and pronunciation dictionary generator. SLT 2008: 217-220 - 2007
- [c29]Steve Renals, Thomas Hain, Hervé Bourlard:
Recognition and understanding of meetings the AMI and AMIDA projects. ASRU 2007: 238-247 - [c28]Thomas Hain, Lukás Burget, John Dines, Giulia Garau, Martin Karafiát, David A. van Leeuwen, Mike Lincoln, Vincent Wan:
The 2007 AMI(DA) System for Meeting Transcription. CLEAR 2007: 414-428 - [c27]Thomas Hain, Vincent Wan, Lukás Burget, Martin Karafiát, John Dines, Jithendra Vepa, Giulia Garau, Mike Lincoln:
The AMI System for the Transcription of Speech in Meetings. ICASSP (4) 2007: 357-360 - [c26]Matthew Gibson, Thomas Hain:
Temporal masking for unsupervised minimum Bayes risk speaker adaptation. INTERSPEECH 2007: 238-241 - [c25]Martin Karafiát, Lukás Burget, Jan Cernocký, Thomas Hain:
Application of CMLLR in narrow band wide band adapted systems. INTERSPEECH 2007: 282-285 - 2006
- [j3]Thomas Hain, Philip C. Woodland, Gunnar Evermann, Mark J. F. Gales, Xunying Liu, Gareth L. Moore, Daniel Povey, Lan Wang:
Corrections to "Automatic Transcription of Conversational Telephone Speech". IEEE Trans. Speech Audio Process. 14(2): 727-727 (2006) - [c24]Vincent Wan, Thomas Hain:
Strategies for Language Model Web-Data Collection. ICASSP (1) 2006: 1069-1072 - [c23]John Dines, Jithendra Vepa, Thomas Hain:
The segmentation of multi-channel meeting recordings for automatic speech recognition. INTERSPEECH 2006 - [c22]Matthew Gibson, Thomas Hain:
Hypothesis spaces for minimum Bayes risk training in large vocabulary speech recognition. INTERSPEECH 2006 - [c21]Esmeralda Uraga, Thomas Hain:
Automatic speech recognition experiments with articulatory data. INTERSPEECH 2006 - [c20]Marc A. Al-Hames, Thomas Hain, Jan Cernocký, Sascha Schreiber, Mannes Poel, Ronald Müller, Sébastien Marcel, David A. van Leeuwen, Jean-Marc Odobez, Sileye O. Ba, Hervé Bourlard, Fabien Cardinaux, Daniel Gatica-Perez, Adam Janin, Petr Motlícek, Stephan Reiter, Steve Renals, Jeroen van Rest, Rutger Rienks, Gerhard Rigoll, Kevin Smith, Andrew H. C. Thean, Pavel Zemcík:
Audio-Visual Processing in Meetings: Seven Questions and Current AMI Answers. MLMI 2006: 24-35 - [c19]Darren Moore, John Dines, Mathew Magimai-Doss, Jithendra Vepa, Octavian Cheng, Thomas Hain:
Juicer: A Weighted Finite-State Transducer Speech Decoder. MLMI 2006: 285-296 - [c18]Thomas Hain, Lukás Burget, John Dines, Giulia Garau, Martin Karafiát, Mike Lincoln, Jithendra Vepa, Vincent Wan:
The AMI Meeting Transcription System: Progress and Performance. MLMI 2006: 419-431 - 2005
- [j2]Thomas Hain:
Implicit modelling of pronunciation variation in automatic speech recognition. Speech Commun. 46(2): 171-188 (2005) - [j1]Thomas Hain, Philip C. Woodland, Gunnar Evermann, Mark J. F. Gales, Xunying Liu, Gareth L. Moore, Daniel Povey, Lan Wang:
Automatic transcription of conversational telephone speech. IEEE Trans. Speech Audio Process. 13(6): 1173-1185 (2005) - [c17]Thomas Hain, David Mercer:
Fast Floating Point Square Root. AMCS 2005: 33-39 - [c16]Thomas Hain, David Langan:
A Fast, Practical Algorithm for the Trapezoidation of Simple Polygons. CISST 2005: 98-108 - [c15]Giulia Garau, Steve Renals, Thomas Hain:
Applying vocal tract length normalization to meeting recordings. INTERSPEECH 2005: 265-268 - [c14]Thomas Hain, John Dines, Giulia Garau, Martin Karafiát, Darren Moore, Vincent Wan, Roeland Ordelman, Steve Renals:
Transcription of conference room meetings: an investigation. INTERSPEECH 2005: 1661-1664 - [c13]Jean Carletta, Simone Ashby, Sebastien Bourban, Mike Flynn, Maël Guillemot, Thomas Hain, Jaroslav Kadlec, Vasilis Karaiskos, Wessel Kraaij, Melissa Kronenthal, Guillaume Lathoud, Mike Lincoln, Agnes Lisowska, Iain McCowan, Wilfried M. Post, Dennis Reidsma, Pierre Wellner:
The AMI Meeting Corpus: A Pre-announcement. MLMI 2005: 28-39 - [c12]Thomas Hain, Lukás Burget, John Dines, Iain McCowan, Giulia Garau, Martin Karafiát, Mike Lincoln, Darren Moore, Vincent Wan, Roeland Ordelman, Steve Renals:
The Development of the AMI System for the Transcription of Speech in Meetings. MLMI 2005: 344-356 - [c11]Thomas Hain, Lukás Burget, John Dines, Giulia Garau, Martin Karafiát, Mike Lincoln, Iain McCowan, Darren Moore, Vincent Wan, Roeland Ordelman, Steve Renals:
The 2005 AMI System for the Transcription of Speech in Meetings. MLMI 2005: 450-462 - 2004
- [c10]Gunnar Evermann, Ho Yin Chan, Mark J. F. Gales, Thomas Hain, Xunying Liu, David Mrva, Lan Wang, Philip C. Woodland:
Development of the 2003 CU-HTK conversational telephone speech transcription system. ICASSP (1) 2004: 249-252 - [c9]Do Yeong Kim, Srinivasan Umesh, Mark J. F. Gales, Thomas Hain, Philip C. Woodland:
Using VTLN for broadcast news transcription. INTERSPEECH 2004: 1953-1956 - 2001
- [c8]Thomas Hain, Philip C. Woodland, Gunnar Evermann, Daniel Povey:
New features in the CU-HTK system for transcription of conversational telephone speech. ICASSP 2001: 57-60 - 2000
- [c7]Thomas Hain, Philip C. Woodland:
Modelling sub-phone insertions and deletions in continuous speech recognition. INTERSPEECH 2000: 172-175
1990 – 1999
- 1999
- [c6]Thomas Hain, Philip C. Woodland, Thomas Niesler, Edward W. D. Whittaker:
The 1998 HTK system for transcription of conversational telephone speech. ICASSP 1999: 57-60 - [c5]Thomas Hain, Philip C. Woodland:
Dynamic HMM selection for continuous speech recognition. EUROSPEECH 1999 - [c4]Philip C. Woodland, J. J. Odell, Thomas Hain, Gareth L. Moore, Thomas Niesler, Andreas Tuerk, Edward W. D. Whittaker:
Improvements in accuracy and speed in the HTK broadcast news transcription system. EUROSPEECH 1999: 1043-1046 - 1998
- [c3]Philip C. Woodland, Thomas Hain, Sue E. Johnson, Thomas Niesler, Andreas Tuerk, Steve J. Young:
Experiments in broadcast news transcription. ICASSP 1998: 909-912 - [c2]Thomas Hain, Philip C. Woodland:
Segmentation and classification of broadcast news audio. ICSLP 1998 - 1994
- [c1]Bemd Hurtgen, Thomas Hain:
On the convergence of fractal transforms. ICASSP (5) 1994: 561-564
Coauthor Index
Rama Sanand Doddipatla
aka: Rama Doddipatla
aka: Rama Doddipatla
Md Asif Jalal
aka: Md. Asif Jalal
aka: Md. Asif Jalal
Oscar Saz-Torralba
aka: Oscar Saz
aka: Oscar Saz
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 2025-01-21 00:14 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:
