John R. Hershey

185 papers A* 6A 27B 2C 7Misc 41Journal 61Unranked 33

Year	Rank	Type	Title / Venue / Authors
2025	—	`conf`	Generative Data Augmentation Challenge: Synthesis of Room Acoustics for Speaker Distance Estimation. ICASSP Workshops Jackie Lin, Georg Götz, Hermes Sampedro Llopis, Haukur Hafsteinsson, Steinar Guðjónsson, Daniel Gert Nielsen, Finnur Pind, Paris Smaragdis, Dinesh Manocha, John R. Hershey, Trausti T. Kristjansson, Minje Kim
2025	J	`jnl`	Generative Data Augmentation Challenge: Synthesis of Room Acoustics for Speaker Distance Estimation. CoRR Jackie Lin, Georg Götz, Hermes Sampedro Llopis, Haukur Hafsteinsson, Steinar Guðjónsson, Daniel Gert Nielsen, Finnur Pind, Paris Smaragdis, Dinesh Manocha, John R. Hershey, Trausti T. Kristjansson, Minje Kim
2025	—	`conf`	Generative Data Augmentation Challenge: Zero-Shot Speech Synthesis for Personalized Speech Enhancement. ICASSP Workshops Jae-Sung Bae, Anastasia Kuznetsova, Dinesh Manocha, John R. Hershey, Trausti T. Kristjansson, Minje Kim
2025	J	`jnl`	Generative Data Augmentation Challenge: Zero-Shot Speech Synthesis for Personalized Speech Enhancement. CoRR Jae-Sung Bae, Anastasia Kuznetsova, Dinesh Manocha, John R. Hershey, Trausti T. Kristjansson, Minje Kim
2025	A*	`conf`	I-Con: A Unifying Framework for Representation Learning. ICLR Shaden Naif Alshammari, John R. Hershey, Axel Feldmann, William T. Freeman, Mark Hamilton
2025	J	`jnl`	I-Con: A Unifying Framework for Representation Learning. CoRR Shaden Naif Alshammari, John R. Hershey, Axel Feldmann, William T. Freeman, Mark Hamilton
2025	J	`jnl`	Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge. Comput. Speech Lang. Simon Leglaive, Matthieu Fraticelli, Hend Elghazaly, Léonie Borne, Mostafa Sadeghi, Scott Wisdom, Manuel Pariente, John R. Hershey, Daniel Pressnitzer, Jon P. Barker
2025	J	`jnl`	Recomposer: Event-roll-guided generative audio editing. CoRR Daniel P. W. Ellis, Eduardo Fonseca, Ron J. Weiss, Kevin W. Wilson, Scott Wisdom, Hakan Erdogan, John R. Hershey, Aren Jansen, R. Channing Moore, Manoj Plakal
2025	—	`conf`	Source Separation by Flow Matching. WASPAA Robin Scheibler, John R. Hershey, Arnaud Doucet, Henry Li
2025	J	`jnl`	Source Separation by Flow Matching. CoRR Robin Scheibler, John R. Hershey, Arnaud Doucet, Henry Li
2025	Misc	`conf`	Towards Sub-millisecond Latency Real-Time Speech Enhancement Models on Hearables. ICASSP Artem Dementyev, Chandan K. A. Reddy, Scott Wisdom, Navin Chatlani, John R. Hershey, Richard F. Lyon
2024	J	`jnl`	Objective and subjective evaluation of speech enhancement methods in the UDASE task of the 7th CHiME challenge. CoRR Simon Leglaive, Matthieu Fraticelli, Hend Elghazaly, Léonie Borne, Mostafa Sadeghi, Scott Wisdom, Manuel Pariente, John R. Hershey, Daniel Pressnitzer, Jon P. Barker
2024	A*	`conf`	Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language. CVPR Mark Hamilton, Andrew Zisserman, John R. Hershey, William T. Freeman
2024	J	`jnl`	Separating the "Chirp" from the "Chat": Self-supervised Visual Grounding of Sound and Language. CoRR Mark Hamilton, Andrew Zisserman, John R. Hershey, William T. Freeman
2024	J	`jnl`	Towards sub-millisecond latency real-time speech enhancement models on hearables. CoRR Artem Dementyev, Chandan K. A. Reddy, Scott Wisdom, Navin Chatlani, John R. Hershey, Richard F. Lyon
2024	J	`jnl`	Understanding Learning with Sliced-Wasserstein Requires Rethinking Informative Slices. CoRR Huy Tran, Yikun Bai, Ashkan Shahbazi, John R. Hershey, Soheil Kolouri
2024	A	`conf`	Unsupervised Improved MVDR Beamforming for Sound Enhancement. INTERSPEECH Jacob Kealey, John R. Hershey, François Grondin
2024	J	`jnl`	Unsupervised Improved MVDR Beamforming for Sound Enhancement. CoRR Jacob Kealey, John R. Hershey, François Grondin
2024	Misc	`conf`	Unsupervised Multi-Channel Separation And Adaptation. ICASSP Cong Han, Kevin W. Wilson, Scott Wisdom, John R. Hershey
2023	J	`jnl`	AudioSlots: A slot-centric generative model for audio separation. CoRR Pradyumna Reddy, Scott Wisdom, Klaus Greff, John R. Hershey, Thomas Kipf
2023	—	`conf`	Audioslots: A Slot-Centric Generative Model For Audio Separation. ICASSP Workshops Pradyumna Reddy, Scott Wisdom, Klaus Greff, John R. Hershey, Thomas Kipf
2023	J	`jnl`	The CHiME-7 UDASE task: Unsupervised domain adaptation for conversational speech enhancement. CoRR Simon Leglaive, Léonie Borne, Efthymios Tzinis, Mostafa Sadeghi, Matthieu Fraticelli, Scott Wisdom, Manuel Pariente, Daniel Pressnitzer, John R. Hershey
2023	A	`conf`	TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition. INTERSPEECH Hakan Erdogan, Scott Wisdom, Xuankai Chang, Zalán Borsos, Marco Tagliasacchi, Neil Zeghidour, John R. Hershey
2023	J	`jnl`	TokenSplit: Using Discrete Speech Representations for Direct, Refined, and Transcript-Conditioned Speech Separation and Recognition. CoRR Hakan Erdogan, Scott Wisdom, Xuankai Chang, Zalán Borsos, Marco Tagliasacchi, Neil Zeghidour, John R. Hershey
2023	J	`jnl`	Unsupervised Multi-channel Separation and Adaptation. CoRR Cong Han, Kevin W. Wilson, Scott Wisdom, John R. Hershey
2022	Misc	`conf`	Adapting Speech Separation to Real-World Meetings using Mixture Invariant Training. ICASSP Aswin Sivaraman, Scott Wisdom, Hakan Erdogan, John R. Hershey
2022	—	`conf`	AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation. ECCV (37) Efthymios Tzinis, Scott Wisdom, Tal Remez, John R. Hershey
2022	J	`jnl`	AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation. CoRR Efthymios Tzinis, Scott Wisdom, Tal Remez, John R. Hershey
2022	J	`jnl`	CycleGAN-Based Unpaired Speech Dereverberation. CoRR Hannah Muckenhirn, Aleksandr Safin, Hakan Erdogan, Felix de Chaumont Quitry, Marco Tagliasacchi, Scott Wisdom, John R. Hershey
2022	A	`conf`	CycleGAN-based Unpaired Speech Dereverberation. INTERSPEECH Hannah Muckenhirn, Aleksandr Safin, Hakan Erdogan, Felix de Chaumont Quitry, Marco Tagliasacchi, Scott Wisdom, John R. Hershey
2022	A	`conf`	Distance-Based Sound Separation. INTERSPEECH Katharine Patterson, Kevin W. Wilson, Scott Wisdom, John R. Hershey
2022	J	`jnl`	Distance-Based Sound Separation. CoRR Katharine Patterson, Kevin W. Wilson, Scott Wisdom, John R. Hershey
2022	Misc	`conf`	Improving Bird Classification with Unsupervised Sound Separation. ICASSP Tom Denton, Scott Wisdom, John R. Hershey
2021	J	`jnl`	Adapting Speech Separation to Real-World Meetings Using Mixture Invariant Training. CoRR Aswin Sivaraman, Scott Wisdom, Hakan Erdogan, John R. Hershey
2021	A	`conf`	Continuous Speech Separation Using Speaker Inventory for Long Recording. Interspeech Cong Han, Yi Luo, Chenda Li, Tianyan Zhou, Keisuke Kinoshita, Shinji Watanabe, Marc Delcroix, Hakan Erdogan, John R. Hershey, Nima Mesgarani, Zhuo Chen
2021	—	`conf`	DF-Conformer: Integrated Architecture of Conv-Tasnet and Conformer Using Linear Complexity Self-Attention for Speech Enhancement. WASPAA Yuma Koizumi, Shigeki Karita, Scott Wisdom, Hakan Erdogan, John R. Hershey, Llion Jones, Michiel Bacchiani
2021	J	`jnl`	DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement. CoRR Yuma Koizumi, Shigeki Karita, Scott Wisdom, Hakan Erdogan, John R. Hershey, Llion Jones, Michiel Bacchiani
2021	Misc	`conf`	End-To-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings. ICASSP Soumi Maiti, Hakan Erdogan, Kevin W. Wilson, Scott Wisdom, Shinji Watanabe, John R. Hershey
2021	J	`jnl`	End-to-End Diarization for Variable Number of Speakers with Local-Global Networks and Discriminative Speaker Embeddings. CoRR Soumi Maiti, Hakan Erdogan, Kevin W. Wilson, Scott Wisdom, Shinji Watanabe, John R. Hershey
2021	J	`jnl`	Improving On-Screen Sound Separation for Open Domain Videos with Audio-Visual Self-attention. CoRR Efthymios Tzinis, Scott Wisdom, Tal Remez, John R. Hershey
2021	—	`conf`	Integration of Speech Separation, Diarization, and Recognition for Multi-Speaker Meetings: System Description, Comparison, and Analysis. SLT Desh Raj, Pavel Denisov, Zhuo Chen, Hakan Erdogan, Zili Huang, Maokui He, Shinji Watanabe, Jun Du, Takuya Yoshioka, Yi Luo, Naoyuki Kanda, Jinyu Li, Scott Wisdom, John R. Hershey
2021	A*	`conf`	Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds. ICLR Efthymios Tzinis, Scott Wisdom, Aren Jansen, Shawn Hershey, Tal Remez, Dan Ellis, John R. Hershey
2021	—	`conf`	Self-Supervised Learning from Automatically Separated Sound Scenes. WASPAA Eduardo Fonseca, Aren Jansen, Daniel P. W. Ellis, Scott Wisdom, Marco Tagliasacchi, John R. Hershey, Manoj Plakal, Shawn Hershey, R. Channing Moore, Xavier Serra
2021	J	`jnl`	Self-Supervised Learning from Automatically Separated Sound Scenes. CoRR Eduardo Fonseca, Aren Jansen, Daniel P. W. Ellis, Scott Wisdom, Marco Tagliasacchi, John R. Hershey, Manoj Plakal, Shawn Hershey, R. Channing Moore, Xavier Serra
2021	—	`conf`	Sequential Multi-Frame Neural Beamforming for Speech Separation and Enhancement. SLT Zhong-Qiu Wang, Hakan Erdogan, Scott Wisdom, Kevin W. Wilson, Desh Raj, Shinji Watanabe, Zhuo Chen, John R. Hershey
2021	Misc	`conf`	Sound Event Detection and Separation: A Benchmark on Desed Synthetic Soundscapes. ICASSP Nicolas Turpault, Romain Serizel, Scott Wisdom, Hakan Erdogan, John R. Hershey, Eduardo Fonseca, Prem Seetharaman, Justin Salamon
2021	—	`conf`	Sparse, Efficient, and Semantic Mixture Invariant Training: Taming In-the-Wild Unsupervised Sound Separation. WASPAA Scott Wisdom, Aren Jansen, Ron J. Weiss, Hakan Erdogan, John R. Hershey
2021	J	`jnl`	Sparse, Efficient, and Semantic Mixture Invariant Training: Taming In-the-Wild Unsupervised Sound Separation. CoRR Scott Wisdom, Aren Jansen, Ron J. Weiss, Hakan Erdogan, John R. Hershey
2021	Misc	`conf`	What's all the Fuss about Free Universal Sound Separation Data? ICASSP Scott Wisdom, Hakan Erdogan, Daniel P. W. Ellis, Romain Serizel, Nicolas Turpault, Eduardo Fonseca, Justin Salamon, Prem Seetharaman, John R. Hershey
2020	J	`jnl`	Continuous Speech Separation Using Speaker Inventory for Long Multi-talker Recording. CoRR Cong Han, Yi Luo, Chenda Li, Tianyan Zhou, Keisuke Kinoshita, Shinji Watanabe, Marc Delcroix, Hakan Erdogan, John R. Hershey, Nima Mesgarani, Zhuo Chen
2020	J	`jnl`	Improving Sound Event Detection In Domestic Environments Using Sound Separation. CoRR Nicolas Turpault, Scott Wisdom, Hakan Erdogan, John R. Hershey, Romain Serizel, Eduardo Fonseca, Prem Seetharaman, Justin Salamon
2020	—	`conf`	Improving Sound Event Detection in Domestic Environments using Sound Separation. DCASE Nicolas Turpault, Scott Wisdom, Hakan Erdogan, John R. Hershey, Romain Serizel, Eduardo Fonseca, Prem Seetharaman, Justin Salamon
2020	Misc	`conf`	Improving Universal Sound Separation Using Sound Classification. ICASSP Efthymios Tzinis, Scott Wisdom, John R. Hershey, Aren Jansen, Daniel P. W. Ellis
2020	J	`jnl`	Integration of speech separation, diarization, and recognition for multi-speaker meetings: System description, comparison, and analysis. CoRR Desh Raj, Pavel Denisov, Zhuo Chen, Hakan Erdogan, Zili Huang, Mao-Kui He, Shinji Watanabe, Jun Du, Takuya Yoshioka, Yi Luo, Naoyuki Kanda, Jinyu Li, Scott Wisdom, John R. Hershey
2020	J	`jnl`	Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds. CoRR Efthymios Tzinis, Scott Wisdom, Aren Jansen, Shawn Hershey, Tal Remez, Daniel P. W. Ellis, John R. Hershey
2020	J	`jnl`	Sound Event Detection and Separation: a Benchmark on Desed Synthetic Soundscapes. CoRR Nicolas Turpault, Romain Serizel, Scott Wisdom, Hakan Erdogan, John R. Hershey, Eduardo Fonseca, Prem Seetharaman, Justin Salamon
2020	A*	`conf`	Unsupervised Sound Separation Using Mixture Invariant Training. NeurIPS Scott Wisdom, Efthymios Tzinis, Hakan Erdogan, Ron J. Weiss, Kevin W. Wilson, John R. Hershey
2020	J	`jnl`	Unsupervised Sound Separation Using Mixtures of Mixtures. CoRR Scott Wisdom, Efthymios Tzinis, Hakan Erdogan, Ron J. Weiss, Kevin W. Wilson, John R. Hershey
2020	J	`jnl`	What's All the FUSS About Free Universal Sound Separation Data? CoRR Scott Wisdom, Hakan Erdogan, Daniel P. W. Ellis, Romain Serizel, Nicolas Turpault, Eduardo Fonseca, Justin Salamon, Prem Seetharaman, John R. Hershey
2019	J	`jnl`	Adversarial training and decoding strategies for end-to-end neural conversation models. Comput. Speech Lang. Takaaki Hori, Wen Wang, Yusuke Koji, Chiori Hori, Bret Harsham, John R. Hershey
2019	J	`jnl`	Alternating Between Spectral and Spatial Estimation for Speech Separation and Enhancement. CoRR Zhong-Qiu Wang, Scott Wisdom, Kevin W. Wilson, John R. Hershey
2019	Misc	`conf`	Differentiable Consistency Constraints for Improved Deep Speech Enhancement. ICASSP Scott Wisdom, John R. Hershey, Kevin W. Wilson, Jeremy Thorpe, Michael Chinen, Brian Patton, Rif A. Saurous
2019	A	`conf`	End-to-End Multilingual Multi-Speaker Speech Recognition. INTERSPEECH Hiroshi Seki, Takaaki Hori, Shinji Watanabe, Jonathan Le Roux, John R. Hershey
2019	J	`jnl`	Improving Universal Sound Separation Using Sound Classification. CoRR Efthymios Tzinis, Scott Wisdom, John R. Hershey, Aren Jansen, Daniel P. W. Ellis
2019	J	`jnl`	Phasebook and Friends: Leveraging Discrete Representations for Source Separation. IEEE J. Sel. Top. Signal Process. Jonathan Le Roux, Gordon Wichern, Shinji Watanabe, Andy M. Sarroff, John R. Hershey
2019	Misc	`conf`	SDR - Half-baked or Well Done? ICASSP Jonathan Le Roux, Scott Wisdom, Hakan Erdogan, John R. Hershey
2019	Misc	`conf`	The Phasebook: Building Complex Masks via Discrete Representations for Source Separation. ICASSP Jonathan Le Roux, Gordon Wichern, Shinji Watanabe, Andy M. Sarroff, John R. Hershey
2019	—	`conf`	Universal Sound Separation. WASPAA Ilya Kavalerov, Scott Wisdom, Hakan Erdogan, Brian Patton, Kevin W. Wilson, Jonathan Le Roux, John R. Hershey
2019	J	`jnl`	Universal Sound Separation. CoRR Ilya Kavalerov, Scott Wisdom, Hakan Erdogan, Brian Patton, Kevin W. Wilson, Jonathan Le Roux, John R. Hershey
2019	A	`conf`	VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking. INTERSPEECH Quan Wang, Hannah Muckenhirn, Kevin W. Wilson, Prashant Sridhar, Zelin Wu, John R. Hershey, Rif A. Saurous, Ron J. Weiss, Ye Jia, Ignacio López-Moreno
2018	—	`conf`	A Purely End-to-End System for Multi-speaker Speech Recognition. ACL (1) Hiroshi Seki, Takaaki Hori, Shinji Watanabe, Jonathan Le Roux, John R. Hershey
2018	J	`jnl`	A Purely End-to-end System for Multi-speaker Speech Recognition. CoRR Hiroshi Seki, Takaaki Hori, Shinji Watanabe, Jonathan Le Roux, John R. Hershey
2018	Misc	`conf`	Alternative Objective Functions for Deep Clustering. ICASSP Zhong-Qiu Wang, Jonathan Le Roux, John R. Hershey
2018	Misc	`conf`	An End-to-End Language-Tracking Speech Recognizer for Mixed-Language Speech. ICASSP Hiroshi Seki, Shinji Watanabe, Takaaki Hori, Jonathan Le Roux, John R. Hershey
2018	J	`jnl`	Differentiable Consistency Constraints for Improved Deep Speech Enhancement. CoRR Scott Wisdom, John R. Hershey, Kevin W. Wilson, Jeremy Thorpe, Michael Chinen, Brian Patton, Rif A. Saurous
2018	Misc	`conf`	End-to-End Multi-Speaker Speech Recognition. ICASSP Shane Settle, Jonathan Le Roux, Takaaki Hori, Shinji Watanabe, John R. Hershey
2018	A	`conf`	End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction. INTERSPEECH Zhong-Qiu Wang, Jonathan Le Roux, DeLiang Wang, John R. Hershey
2018	J	`jnl`	End-to-End Speech Separation with Unfolded Iterative Phase Reconstruction. CoRR Zhong-Qiu Wang, Jonathan Le Roux, DeLiang Wang, John R. Hershey
2018	—	`conf`	Exploring Tradeoffs in Models for Low-Latency Speech Enhancement. IWAENC Kevin W. Wilson, Michael Chinen, Jeremy Thorpe, Brian Patton, John R. Hershey, Rif A. Saurous, Jan Skoglund, Richard F. Lyon
2018	J	`jnl`	Exploring Tradeoffs in Models for Low-latency Speech Enhancement. CoRR Kevin W. Wilson, Michael Chinen, Jeremy Thorpe, Brian Patton, John R. Hershey, Rif A. Saurous, Jan Skoglund, Richard F. Lyon
2018	Misc	`conf`	Multi-Channel Deep Clustering: Discriminative Spectral and Spatial Embeddings for Speaker-Independent Speech Separation. ICASSP Zhong-Qiu Wang, Jonathan Le Roux, John R. Hershey
2018	J	`jnl`	Phasebook and Friends: Leveraging Discrete Representations for Source Separation. CoRR Jonathan Le Roux, Gordon Wichern, Shinji Watanabe, Andy M. Sarroff, John R. Hershey
2018	J	`jnl`	SDR - half-baked or well done? CoRR Jonathan Le Roux, Scott Wisdom, Hakan Erdogan, John R. Hershey
2018	Misc	`conf`	Speaker Adaptation for Multichannel End-to-End Speech Recognition. ICASSP Tsubasa Ochiai, Shinji Watanabe, Shigeru Katagiri, Takaaki Hori, John R. Hershey
2018	J	`jnl`	VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking. CoRR Quan Wang, Hannah Muckenhirn, Kevin W. Wilson, Prashant Sridhar, Zelin Wu, John R. Hershey, Rif A. Saurous, Ron J. Weiss, Ye Jia, Ignacio López-Moreno
2017	A*	`conf`	Attention-Based Multimodal Fusion for Video Description. ICCV Chiori Hori, Takaaki Hori, Teng-Yok Lee, Ziming Zhang, Bret Harsham, John R. Hershey, Tim K. Marks, Kazuhiro Sumi
2017	J	`jnl`	Attention-Based Multimodal Fusion for Video Description. CoRR Chiori Hori, Takaaki Hori, Teng-Yok Lee, Kazuhiro Sumi, John R. Hershey, Tim K. Marks
2017	J	`jnl`	Deep Long Short-Term Memory Adaptive Beamforming Networks For Multichannel Robust Speech Recognition. CoRR Zhong Meng, Shinji Watanabe, John R. Hershey, Hakan Erdogan
2017	—	`ch.`	Deep Recurrent Networks for Separation and Recognition of Single-Channel Speech in Nonstationary Background Audio. New Era for Robust Speech Recognition, Exploiting Deep Learning Hakan Erdogan, John R. Hershey, Shinji Watanabe, Jonathan Le Roux
2017	Misc	`conf`	Deep clustering and conventional networks for music separation: Stronger together. ICASSP Yi Luo, Zhuo Chen, John R. Hershey, Jonathan Le Roux, Nima Mesgarani
2017	Misc	`conf`	Deep long short-term memory adaptive beamforming networks for multichannel robust speech recognition. ICASSP Zhong Meng, Shinji Watanabe, John R. Hershey, Hakan Erdogan
2017	—	`ch.`	Discriminative Beamforming with Phase-Aware Neural Networks for Speech Enhancement and Recognition. New Era for Robust Speech Recognition, Exploiting Deep Learning Xiong Xiao, Shinji Watanabe, Hakan Erdogan, Michael I. Mandel, Liang Lu, John R. Hershey, Michael L. Seltzer, Guoguo Chen, Yu Zhang, Dong Yu
2017	C	`conf`	Early and late integration of audio features for automatic video description. ASRU Chiori Hori, Takaaki Hori, Tim K. Marks, John R. Hershey
2017	J	`jnl`	Hybrid CTC/Attention Architecture for End-to-End Speech Recognition. IEEE J. Sel. Top. Signal Process. Shinji Watanabe, Takaaki Hori, Suyoun Kim, John R. Hershey, Tomoki Hayashi
2017	—	`conf`	Joint CTC/attention decoding for end-to-end speech recognition. ACL (1) Takaaki Hori, Shinji Watanabe, John R. Hershey
2017	C	`conf`	Language independent end-to-end architecture for joint language identification and speech recognition. ASRU Shinji Watanabe, Takaaki Hori, John R. Hershey
2017	C	`conf`	Multi-level language modeling and decoding for open vocabulary end-to-end speech recognition. ASRU Takaaki Hori, Shinji Watanabe, John R. Hershey
2017	J	`jnl`	Multi-microphone speech recognition integrating beamforming, robust feature extraction, and advanced DNN/RNN backend. Comput. Speech Lang. Takaaki Hori, Zhuo Chen, Hakan Erdogan, John R. Hershey, Jonathan Le Roux, Vikramjit Mitra, Shinji Watanabe
2017	A*	`conf`	Multichannel End-to-end Speech Recognition. ICML Tsubasa Ochiai, Shinji Watanabe, Takaaki Hori, John R. Hershey
2017	J	`jnl`	Multichannel End-to-end Speech Recognition. CoRR Tsubasa Ochiai, Shinji Watanabe, Takaaki Hori, John R. Hershey
2017	—	`book`	New Era for Robust Speech Recognition, Exploiting Deep Learning. Shinji Watanabe, Marc Delcroix, Florian Metze, John R. Hershey
2017	—	`ch.`	Novel Deep Architectures in Speech Processing. New Era for Robust Speech Recognition, Exploiting Deep Learning John R. Hershey, Jonathan Le Roux, Shinji Watanabe, Scott Wisdom, Zhuo Chen, Yusuf Ziya Isik
2017	—	`ch.`	Preliminaries. New Era for Robust Speech Recognition, Exploiting Deep Learning Shinji Watanabe, Marc Delcroix, Florian Metze, John R. Hershey
2017	J	`jnl`	Prior-based Binary Masking and Discriminative Methods for Reverberant and Noisy Speech Recognition Using Distant Stereo Microphones. J. Inf. Process. Yuuki Tachioka, Shinji Watanabe, Jonathan Le Roux, John R. Hershey
2017	Misc	`conf`	Student-teacher network learning with enhanced features. ICASSP Shinji Watanabe, Takaaki Hori, Jonathan Le Roux, John R. Hershey
2017	—	`ch.`	Toolkits for Robust Speech Processing. New Era for Robust Speech Recognition, Exploiting Deep Learning Shinji Watanabe, Takaaki Hori, Yajie Miao, Marc Delcroix, Florian Metze, John R. Hershey
2017	J	`jnl`	Unified Architecture for Multichannel End-to-End Speech Recognition With Neural Beamforming. IEEE J. Sel. Top. Signal Process. Tsubasa Ochiai, Shinji Watanabe, Takaaki Hori, John R. Hershey, Xiong Xiao
2016	A	`conf`	Context-Sensitive and Role-Dependent Spoken Language Understanding Using Bidirectional and Attention LSTMs. INTERSPEECH Chiori Hori, Takaaki Hori, Shinji Watanabe, John R. Hershey
2016	J	`jnl`	Deep Clustering and Conventional Networks for Music Separation: Stronger Together. CoRR Yi Luo, Zhuo Chen, John R. Hershey, Jonathan Le Roux, Nima Mesgarani
2016	Misc	`conf`	Deep beamforming networks for multi-channel speech recognition. ICASSP Xiong Xiao, Shinji Watanabe, Hakan Erdogan, Liang Lu, John R. Hershey, Michael L. Seltzer, Guoguo Chen, Yu Zhang, Michael I. Mandel, Dong Yu
2016	Misc	`conf`	Deep clustering: Discriminative embeddings for segmentation and separation. ICASSP John R. Hershey, Zhuo Chen, Jonathan Le Roux, Shinji Watanabe
2016	Misc	`conf`	Deep unfolding for multichannel source separation. ICASSP Scott Wisdom, John R. Hershey, Jonathan Le Roux, Shinji Watanabe
2016	—	`conf`	Dialog state tracking with attention-based sequence-to-sequence learning. SLT Takaaki Hori, Hai Wang, Chiori Hori, Shinji Watanabe, Bret Harsham, Jonathan Le Roux, John R. Hershey, Yusuke Koji, Yi Jing, Zhaocheng Zhu, Takeyuki Aikawa
2016	A	`conf`	Driver confusion status detection using recurrent neural networks. ICME Chiori Hori, Shinji Watanabe, Takaaki Hori, Bret A. Harsham, John R. Hershey, Yusuke Koji, Youichi Fujii, Yuki Furumoto
2016	—	`conf`	Full-Capacity Unitary Recurrent Neural Networks. NIPS Scott Wisdom, Thomas Powers, John R. Hershey, Jonathan Le Roux, Les E. Atlas
2016	J	`jnl`	Full-Capacity Unitary Recurrent Neural Networks. CoRR Scott Wisdom, Thomas Powers, John R. Hershey, Jonathan Le Roux, Les E. Atlas
2016	J	`jnl`	Global-Local Face Upsampling Network. CoRR Oncel Tuzel, Yuichi Taguchi, John R. Hershey
2016	A	`conf`	Improved MVDR Beamforming Using Single-Channel Mask Prediction Networks. INTERSPEECH Hakan Erdogan, John R. Hershey, Shinji Watanabe, Michael I. Mandel, Jonathan Le Roux
2016	Misc	`conf`	Minimum word error training of long short-term memory recurrent neural network language models for speech recognition. ICASSP Takaaki Hori, Chiori Hori, Shinji Watanabe, John R. Hershey
2016	A	`conf`	Single-Channel Multi-Speaker Separation Using Deep Clustering. INTERSPEECH Yusuf Ziya Isik, Jonathan Le Roux, Zhuo Chen, Shinji Watanabe, John R. Hershey
2016	J	`jnl`	Single-Channel Multi-Speaker Separation using Deep Clustering. CoRR Yusuf Ziya Isik, Jonathan Le Roux, Zhuo Chen, Shinji Watanabe, John R. Hershey
2015	Misc	`conf`	Deep NMF for speech separation. ICASSP Jonathan Le Roux, John R. Hershey, Felix Weninger
2015	J	`jnl`	Deep clustering: Discriminative embeddings for segmentation and separation. CoRR John R. Hershey, Zhuo Chen, Jonathan Le Roux, Shinji Watanabe
2015	Misc	`conf`	Micbots: Collecting large realistic datasets for speech and audio research using mobile robots. ICASSP Jonathan Le Roux, Emmanuel Vincent, John R. Hershey, Daniel P. W. Ellis
2015	Misc	`conf`	Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks. ICASSP Hakan Erdogan, John R. Hershey, Shinji Watanabe, Jonathan Le Roux
2015	—	`conf`	Speech Enhancement with LSTM Recurrent Neural Networks and its Application to Noise-Robust ASR. LVA/ICA Felix Weninger, Hakan Erdogan, Shinji Watanabe, Emmanuel Vincent, Jonathan Le Roux, John R. Hershey, Björn W. Schuller
2015	A	`conf`	Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks. INTERSPEECH Zhuo Chen, Shinji Watanabe, Hakan Erdogan, John R. Hershey
2015	C	`conf`	The MERL/SRI system for the 3RD CHiME challenge using beamforming, robust feature extraction, and advanced speech recognition. ASRU Takaaki Hori, Zhuo Chen, Hakan Erdogan, John R. Hershey, Jonathan Le Roux, Vikramjit Mitra, Shinji Watanabe
2015	A	`conf`	Uncertainty propagation through deep neural networks. INTERSPEECH Ahmed Hussen Abdelaziz, Shinji Watanabe, John R. Hershey, Emmanuel Vincent, Dorothea Kolossa
2014	A	`conf`	Cost-level integration of statistical and rule-based dialog managers. INTERSPEECH Shinji Watanabe, John R. Hershey, Tim K. Marks, Youichi Fujii, Yusuke Koji
2014	J	`jnl`	Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures. CoRR John R. Hershey, Jonathan Le Roux, Felix Weninger
2014	A	`conf`	Discriminative NMF and its application to single-channel source separation. INTERSPEECH Felix Weninger, Jonathan Le Roux, John R. Hershey, Shinji Watanabe
2014	—	`conf`	Discriminatively trained recurrent neural networks for single-channel speech separation. GlobalSIP Felix Weninger, John R. Hershey, Jonathan Le Roux, Björn W. Schuller
2014	Misc	`conf`	Log-linear dialog manager. ICASSP Hao Tang, Shinji Watanabe, Tim K. Marks, John R. Hershey
2014	Misc	`conf`	Non-negative source-filter dynamical system for speech enhancement. ICASSP Umut Simsekli, Jonathan Le Roux, John R. Hershey
2014	—	`conf`	Sequence discriminative training for low-rank deep neural networks. GlobalSIP Yuuki Tachioka, Shinji Watanabe, Jonathan Le Roux, John R. Hershey
2014	A	`conf`	Sequential maximum mutual information linear discriminant analysis for speech recognition. INTERSPEECH Yuuki Tachioka, Shinji Watanabe, Jonathan Le Roux, John R. Hershey
2013	C	`conf`	A generalized discriminative training framework for system combination. ASRU Yuuki Tachioka, Shinji Watanabe, Jonathan Le Roux, John R. Hershey
2013	Misc	`conf`	Effectiveness of discriminative training and feature transformation for reverberated and noisy speech. ICASSP Yuuki Tachioka, Shinji Watanabe, John R. Hershey
2013	—	`conf`	Ensemble learning for speech enhancement. WASPAA Jonathan Le Roux, Shinji Watanabe, John R. Hershey
2013	—	`conf`	Hierarchical and coupled non-negative dynamical systems with application to audio modeling. WASPAA Umut Simsekli, Jonathan Le Roux, John R. Hershey
2013	Misc	`conf`	Non-negative dynamical system with application to speech and audio. ICASSP Cédric Févotte, Jonathan Le Roux, John R. Hershey
2013	Misc	`conf`	Source localization in reverberant environments using sparse optimization. ICASSP Jonathan Le Roux, Petros T. Boufounos, Kang Kang, John R. Hershey
2013	B	`conf`	Statistical Dialogue Management using Intention Dependency Graph. IJCNLP Koichiro Yoshino, Shinji Watanabe, Jonathan Le Roux, John R. Hershey
2013	Misc	`conf`	Stereo-based feature enhancement using dictionary learning. ICASSP Shinji Watanabe, John R. Hershey
2012	—	`ch.`	Factorial Models for Noise Robust Speech Recognition. Techniques for Noise Robustness in Automatic Speech Recognition John R. Hershey, Steven J. Rennie, Jonathan Le Roux
2012	J	`jnl`	Hidden Markov Acoustic Modeling With Bootstrap and Restructuring for Low-Resourced Languages. IEEE Trans. Speech Audio Process. Xiaodong Cui, Jian Xue, Xin Chen, Peder A. Olsen, Pierre L. Dognin, Upendra V. Chaudhari, John R. Hershey, Bowen Zhou
2012	Misc	`conf`	Indirect model-based speech enhancement. ICASSP Jonathan Le Roux, John R. Hershey
2011	A	`conf`	Acoustic Modeling with Bootstrap and Restructuring Based on Full Covariance. INTERSPEECH Xiaodong Cui, Xin Chen, Jian Xue, Peder A. Olsen, John R. Hershey, Bowen Zhou
2011	Misc	`conf`	Clustering of bootstrapped acoustic model with full covariance. ICASSP Xin Chen, Xiaodong Cui, Jian Xue, Peder A. Olsen, John R. Hershey, Bowen Zhou, Yunxin Zhao
2011	A	`conf`	Entropy-based motion selection for touch-based registration using Rao-Blackwellized particle filtering. IROS Yuichi Taguchi, Tim K. Marks, John R. Hershey
2010	A	`conf`	Modeling posterior probabilities using the linear exponential family. INTERSPEECH Peder A. Olsen, Vaibhava Goel, Charles A. Micchelli, John R. Hershey
2010	J	`jnl`	Monaural speech separation and recognition challenge. Comput. Speech Lang. Martin Cooke, John R. Hershey, Steven J. Rennie
2010	A	`conf`	Restructuring exponential family mixture models. INTERSPEECH Pierre L. Dognin, John R. Hershey, Vaibhava Goel, Peder A. Olsen
2010	A	`conf`	Signal interaction and the devil function. INTERSPEECH John R. Hershey, Peder A. Olsen, Steven J. Rennie
2010	J	`jnl`	Single-Channel Multitalker Speech Recognition. IEEE Signal Process. Mag. Steven J. Rennie, John R. Hershey, Peder A. Olsen
2010	J	`jnl`	Super-human multi-talker speech recognition: A graphical modeling approach. Comput. Speech Lang. John R. Hershey, Steven J. Rennie, Peder A. Olsen, Trausti T. Kristjansson
2010	J	`jnl`	Tracking Motion, Deformation, and Texture Using Conditionally Gaussian Processes. IEEE Trans. Pattern Anal. Mach. Intell. Tim K. Marks, John R. Hershey, Javier R. Movellan
2009	Misc	`conf`	A fast, accurate approximation to log likelihood of Gaussian mixture models. ICASSP Pierre L. Dognin, Vaibhava Goel, John R. Hershey, Peder A. Olsen
2009	C	`conf`	Hierarchical variational loopy belief propagation for multi-talker speech recognition. ASRU Steven J. Rennie, John R. Hershey, Peder A. Olsen
2009	Misc	`conf`	Refactoring acoustic models using variational density approximation. ICASSP Pierre L. Dognin, John R. Hershey, Vaibhava Goel, Peder A. Olsen
2009	A	`conf`	Refactoring acoustic models using variational expectation-maximization. INTERSPEECH Pierre L. Dognin, John R. Hershey, Vaibhava Goel, Peder A. Olsen
2009	Misc	`conf`	Single-channel speech separation and recognition using loopy belief propagation. ICASSP Steven J. Rennie, John R. Hershey, Peder A. Olsen
2009	A	`conf`	Variational loopy belief propagation for multi-talker speech recognition. INTERSPEECH Steven J. Rennie, John R. Hershey, Peder A. Olsen
2008	Misc	`conf`	Accelerated Monte Carlo for Kullback-Leibler divergence between Gaussian mixture models. ICASSP Jia-Yu Chen, John R. Hershey, Peder A. Olsen, Emmanuel Yashchin
2008	Misc	`conf`	Efficient model-based speech separation and denoising using non-negative subspace analysis. ICASSP Steven J. Rennie, John R. Hershey, Peder A. Olsen
2008	Misc	`conf`	Optimizing speech recognition grammars using a measure of similarity between hidden Markov models. ICASSP Binit Mohanty, John R. Hershey, Peder A. Olsen, Suleyman Serdar Kozat, Vaibhava Goel
2008	Misc	`conf`	Variational Bhattacharyya divergence for hidden Markov models. ICASSP John R. Hershey, Peder A. Olsen
2007	—	`conf`	Approximating the Kullback Leibler Divergence Between Gaussian Mixture Models. ICASSP (4) John R. Hershey, Peder A. Olsen
2007	A	`conf`	Bhattacharyya error and divergence using variational importance sampling. INTERSPEECH Peder A. Olsen, John R. Hershey
2007	C	`conf`	Variational Kullback-Leibler divergence for Hidden Markov models. ASRU John R. Hershey, Peder A. Olsen, Steven J. Rennie
2007	A	`conf`	Word confusability - measuring hidden Markov model similarity. INTERSPEECH Jia-Yu Chen, Peder A. Olsen, John R. Hershey
2006	—	`conf`	Single Channel Speech Separation Using Factorial Dynamics. NIPS John R. Hershey, Trausti T. Kristjansson, Steven J. Rennie, Peder A. Olsen
2006	A	`conf`	Super-human multi-talker speech recognition: the IBM 2006 speech separation challenge system. INTERSPEECH Trausti T. Kristjansson, John R. Hershey, Peder A. Olsen, Steven J. Rennie, Ramesh A. Gopinath
2006	—	`conf`	The Iroquois model: using temporal dynamics to separate speakers. SAPA@INTERSPEECH Steven J. Rennie, Peder A. Olsen, John R. Hershey, Trausti T. Kristjansson
2005	—	`—`	Perceptual inference in generative models. John R. Hershey
2004	—	`conf`	3D Tracking of Morphable Objects Using Conditionally Gaussian Nonlinear Filters. CVPR Workshops Tim K. Marks, John R. Hershey, J. Cooper Roddey, Javier R. Movellan
2004	—	`conf`	Audio-visual graphical models for speech processing. ICASSP (5) John R. Hershey, Hagai Attias, Nebojsa Jojic, Trausti T. Kristjansson
2004	—	`conf`	Joint Tracking of Pose, Expression, and Texture using Conditionally Gaussian Filters. NIPS Tim K. Marks, John R. Hershey, J. Cooper Roddey, Javier R. Movellan
2004	—	`conf`	Model-based fusion of bone and air sensors for speech enhancement and robust speech recognition. SAPA@INTERSPEECH John R. Hershey, Trausti T. Kristjansson, Zhengyou Zhang
2004	—	`conf`	Single microphone source separation using high resolution signal reconstruction. ICASSP (2) Trausti T. Kristjansson, Hagai Attias, John R. Hershey
2004	—	`conf`	Stereo Based 3D Tracking and Scene Learning, Employing Particle Filtering within EM. ECCV (4) Trausti T. Kristjansson, Hagai Attias, John R. Hershey
2001	—	`conf`	Audio-Visual Sound Separation Via Hidden Markov Models. NIPS John R. Hershey, Michael Casey
2000	B	`conf`	A Low-Level Cortical Perception Model with Applications to Image Analysis. ICIP Irina F. Gorodnitsky, John R. Hershey
1999	—	`conf`	Audio Vision: Using Audio-Visual Synchrony to Locate Sounds. NIPS John R. Hershey, Javier R. Movellan