default search action
Google
Google Scholar
Semantic Scholar
Internet Archive Scholar
CiteSeerX
ORCIDGil Keren
Person information
Refine list
refinements active!
zoomed in on ?? of ?? records
view refined list in
export refined list as
2020 – today
- 2024
[c19]Puneet Mathur, Zhe Liu, Ke Li, Yingyi Ma, Gil Keren, Zeeshan Ahmed, Dinesh Manocha, Xuedong Zhang:
DOC-RAG: ASR Language Model Personalization with Domain-Distributed Co-occurrence Retrieval Augmentation. LREC/COLING 2024: 5132-5139- [i20]Gil Keren, Wei Zhou, Ozlem Kalinli:
Token-Weighted RNN-T for Learning from Flawed Data. CoRR abs/2406.18108 (2024) - [i19]Desh Raj, Gil Keren, Junteng Jia, Jay Mahadeokar, Ozlem Kalinli:
Faster Speech-LLaMA Inference with Multi-token Prediction. CoRR abs/2409.08148 (2024) - [i18]Yufeng Yang, Desh Raj, Ju Lin, Niko Moritz, Junteng Jia, Gil Keren, Egor Lakomkin, Yiteng Huang, Jacob Donley, Jay Mahadeokar, Ozlem Kalinli:
M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses. CoRR abs/2409.11494 (2024) - [i17]Junteng Jia, Gil Keren, Wei Zhou, Egor Lakomkin, Xiaohui Zhang, Chunyang Wu, Frank Seide, Jay Mahadeokar, Ozlem Kalinli:
Efficient Streaming LLM for Speech Recognition. CoRR abs/2410.03752 (2024) - 2023
- [c18]Gil Keren:
A Token-Wise Beam Search Algorithm for RNN-T. ASRU 2023: 1-8 - [c17]Puneet Mathur, Zhe Liu, Ke Li, Yingyi Ma, Gil Keren, Zeeshan Ahmed, Dinesh Manocha, Xuedong Zhang:
PersonaLM: Language Model Personalization via Domain-distributed Span Aggregated K-Nearest N-gram Retrieval Augmentation. EMNLP (Findings) 2023: 11314-11328 - [c16]Ke Li, Jay Mahadeokar, Jinxi Guo, Yangyang Shi, Gil Keren, Ozlem Kalinli, Michael L. Seltzer, Duc Le:
Improving fast-slow Encoder based Transducer with Streaming Deliberation. ICASSP 2023: 1-5 - [i16]Gil Keren:
A Token-Wise Beam Search Algorithm for RNN-T. CoRR abs/2302.14357 (2023) - [i15]Zhuangqun Huang, Gil Keren, Ziran Jiang, Shashank Jain, David Goss-Grubbs, Nelson Cheng, Farnaz Abtahi, Duc Le, David Zhang, Antony D'Avirro, Ethan Campbell-Taylor, Jessie Salas, Irina-Elena Veliche, Xi Chen:
Text Generation with Speech Synthesis for ASR Data Augmentation. CoRR abs/2305.16333 (2023) - [i14]Shuo Liu, Leda Sari, Chunyang Wu, Gil Keren, Yuan Shangguan, Jay Mahadeokar, Ozlem Kalinli:
Towards Selection of Text-to-speech Data to Augment ASR Training. CoRR abs/2306.00998 (2023) - 2022
- [c15]Weiyi Zheng, Alex Xiao, Gil Keren, Duc Le, Frank Zhang, Christian Fuegen, Ozlem Kalinli, Yatharth Saraf, Abdelrahman Mohamed:
Scaling ASR Improves Zero and Few Shot Learning. INTERSPEECH 2022: 5135-5139 - 2021
- [j4]Shuo Liu
, Gil Keren, Emilia Parada-Cabaleiro, Björn W. Schuller:
N-HANS: A neural network-based toolkit for in-the-wild audio enhancement. Multim. Tools Appl. 80(18): 28365-28389 (2021) - [c14]Ju Lin, Yun Wang, Kaustubh Kalgaonkar, Gil Keren, Didi Zhang, Christian Fuegen:
A Time-Domain Convolutional Recurrent Network for Packet Loss Concealment. ICASSP 2021: 7148-7152 - [c13]Ju Lin, Yun Wang, Kaustubh Kalgaonkar, Gil Keren, Didi Zhang, Christian Fuegen:
A Two-Stage Approach to Speech Bandwidth Extension. Interspeech 2021: 1689-1693 - [c12]Duc Le, Mahaveer Jain, Gil Keren, Suyoun Kim, Yangyang Shi, Jay Mahadeokar, Julian Chan, Yuan Shangguan, Christian Fuegen, Ozlem Kalinli, Yatharth Saraf, Michael L. Seltzer:
Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion. Interspeech 2021: 1772-1776 - [c11]Jay Mahadeokar, Yuan Shangguan, Duc Le, Gil Keren, Hang Su, Thong Le, Ching-Feng Yeh, Christian Fuegen, Michael L. Seltzer:
Alignment Restricted Streaming Recurrent Neural Network Transducer. SLT 2021: 52-59 - [c10]Duc Le, Gil Keren, Julian Chan, Jay Mahadeokar, Christian Fuegen, Michael L. Seltzer:
Deep Shallow Fusion for RNN-T Personalization. SLT 2021: 251-257 - [i13]Duc Le, Mahaveer Jain, Gil Keren, Suyoun Kim, Yangyang Shi, Jay Mahadeokar, Julian Chan, Yuan Shangguan, Christian Fuegen, Ozlem Kalinli, Yatharth Saraf, Michael L. Seltzer:
Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion. CoRR abs/2104.02194 (2021) - [i12]Alex Xiao, Weiyi Zheng, Gil Keren, Duc Le, Frank Zhang, Christian Fuegen, Ozlem Kalinli, Yatharth Saraf, Abdelrahman Mohamed:
Scaling ASR Improves Zero and Few Shot Learning. CoRR abs/2111.05948 (2021) - 2020
- [b1]Gil Keren:
Neural Network Supervision: Notes on Loss Functions, Labels and Confidence Estimation. University of Passau, Germany, 2020 - [j3]Gil Keren, Sivan Sabato, Björn W. Schuller:
Analysis of loss functions for fast single-class classification. Knowl. Inf. Syst. 62(1): 337-358 (2020) - [c9]Mahaveer Jain, Gil Keren, Jay Mahadeokar, Geoffrey Zweig, Florian Metze, Yatharth Saraf:
Contextual RNN-T for Open Domain ASR. INTERSPEECH 2020: 11-15 - [i11]Mahaveer Jain, Gil Keren, Jay Mahadeokar, Yatharth Saraf:
Contextual RNN-T For Open Domain ASR. CoRR abs/2006.03411 (2020) - [i10]Jay Mahadeokar, Yuan Shangguan, Duc Le, Gil Keren, Hang Su, Thong Le, Ching-Feng Yeh, Christian Fuegen, Michael L. Seltzer:
Alignment Restricted Streaming Recurrent Neural Network Transducer. CoRR abs/2011.03072 (2020) - [i9]Duc Le, Gil Keren, Julian Chan, Jay Mahadeokar, Christian Fuegen, Michael L. Seltzer:
Deep Shallow Fusion for RNN-T Personalization. CoRR abs/2011.07754 (2020)
2010 – 2019
- 2019
- [c8]Gil Keren, Sivan Sabato, Björn W. Schuller:
A Walkthrough for the Principle of Logit Separation. IJCAI 2019: 6191-6195 - [c7]Andreas Triantafyllopoulos, Gil Keren, Johannes Wagner, Ingmar Steiner, Björn W. Schuller:
Towards Robust Speech Emotion Recognition Using Deep Residual Networks for Speech Enhancement. INTERSPEECH 2019: 1691-1695 - [i8]Shuo Liu, Gil Keren, Björn W. Schuller:
Single-Channel Speech Separation with Auxiliary Speaker Embeddings. CoRR abs/1906.09997 (2019) - [i7]Shuo Liu, Gil Keren, Björn W. Schuller:
N-HANS: Introducing the Augsburg Neuro-Holistic Audio-eNhancement System. CoRR abs/1911.07062 (2019) - 2018
- [j2]Gil Keren, Nicholas Cummins, Björn W. Schuller:
Calibrated Prediction Intervals for Neural Network Regressors. IEEE Access 6: 54033-54041 (2018) - [c6]Gil Keren, Sivan Sabato, Björn W. Schuller:
Fast Single-Class Classification and the Principle of Logit Separation. ICDM 2018: 227-236 - [p1]Gil Keren, Amr El-Desoky Mousa, Olivier Pietquin, Stefanos Zafeiriou, Björn W. Schuller:
Deep learning for multisensorial and multimodal interaction. The Handbook of Multimodal-Multisensor Interfaces, Volume 2 (2) 2018: 99-128 - [i6]Gil Keren, Maximilian Schmitt, Thomas Kehrenberg, Björn W. Schuller:
Weakly Supervised One-Shot Detection with Attention Siamese Networks. CoRR abs/1801.03329 (2018) - [i5]Gil Keren, Nicholas Cummins, Björn W. Schuller:
Calibrated Prediction Intervals for Neural Network Regressors. CoRR abs/1803.09546 (2018) - [i4]Gil Keren, Jing Han, Björn W. Schuller:
Scaling Speech Enhancement in Unseen Environments with Noise Embeddings. CoRR abs/1810.12757 (2018) - 2017
- [j1]Pantelis E. Eleftheriou, Assaf Hasson, Gil Keren:
On Definable Skolem Functions in Weakly O-Minimal nonvaluational Structures. J. Symb. Log. 82(4): 1482-1495 (2017) - [c5]Gil Keren, Sivan Sabato, Björn W. Schuller:
Tunable Sensitivity to Large Errors in Neural Network Training. AAAI 2017: 2087-2093 - [c4]Shahin Amiriparian, Sergey Pugachevskiy, Nicholas Cummins, Simone Hantke, Jouni Pohjalainen, Gil Keren, Björn W. Schuller:
CAST a database: Rapid targeted large-scale big data acquisition via small-world modelling of social media platforms. ACII 2017: 340-345 - [c3]Gil Keren, Tobias Kirschstein, Erik Marchi, Fabien Ringeval, Björn W. Schuller:
End-to-end learning for dimensional emotion recognition from physiological signals. ICME 2017: 985-990 - [i3]Gil Keren, Sivan Sabato, Björn W. Schuller:
Fast Single-Class Classification and the Principle of Logit Separation. CoRR abs/1705.10246 (2017) - 2016
- [c2]Gil Keren, Björn W. Schuller:
Convolutional RNN: An enhanced model for extracting features from sequential data. IJCNN 2016: 3412-3419 - [c1]Gil Keren, Jun Deng, Jouni Pohjalainen, Björn W. Schuller:
Convolutional Neural Networks with Data Augmentation for Classifying Speakers' Native Language. INTERSPEECH 2016: 2393-2397 - [i2]Gil Keren, Björn W. Schuller:
Convolutional RNN: an Enhanced Model for Extracting Features from Sequential Data. CoRR abs/1602.05875 (2016) - [i1]Gil Keren, Sivan Sabato, Björn W. Schuller:
Tunable Sensitivity to Large Errors in Neural Network Training. CoRR abs/1611.07743 (2016)
Coauthor Index
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 21:59 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:
