John Hershey
John Hershey
Google (formerly MERL, IBM, MSR, UCSD)
Verified email at google.com
Title
Cited by
Cited by
Year
Approximating the Kullback Leibler divergence between Gaussian mixture models
JR Hershey, PA Olsen
2007 IEEE International Conference on Acoustics, Speech and Signal …, 2007
7512007
Deep clustering: Discriminative embeddings for segmentation and separation
JR Hershey, Z Chen, J Le Roux, S Watanabe
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
4932016
Phase-sensitive and recognition-boosted speech separation using deep recurrent neural networks
H Erdogan, JR Hershey, S Watanabe, J Le Roux
2015 IEEE International Conference on Acoustics, Speech and Signal …, 2015
3182015
Speech enhancement with LSTM recurrent neural networks and its application to noise-robust ASR
F Weninger, H Erdogan, S Watanabe, E Vincent, J Le Roux, JR Hershey, ...
International Conference on Latent Variable Analysis and Signal Separation …, 2015
2932015
Audio vision: Using audio-visual synchrony to locate sounds
JR Hershey, JR Movellan
Advances in neural information processing systems, 813-819, 2000
2862000
Single-channel multi-speaker separation using deep clustering
Y Isik, JL Roux, Z Chen, S Watanabe, JR Hershey
arXiv preprint arXiv:1607.02173, 2016
2152016
Discriminatively trained recurrent neural networks for single-channel speech separation
F Weninger, JR Hershey, J Le Roux, B Schuller
2014 IEEE Global Conference on Signal and Information Processing (GlobalSIP …, 2014
2102014
Monaural speech separation and recognition challenge
M Cooke, JR Hershey, SJ Rennie
Computer Speech & Language 24 (1), 1-15, 2010
2022010
Super-human multi-talker speech recognition: A graphical modeling approach
JR Hershey, SJ Rennie, PA Olsen, TT Kristjansson
Computer Speech & Language 24 (1), 45-66, 2010
1782010
Deep unfolding: Model-based inspiration of novel deep architectures
JR Hershey, JL Roux, F Weninger
arXiv preprint arXiv:1409.2574, 2014
1662014
Weak hypothesis generation apparatus and method, learning apparatus and method, detection apparatus and method, facial expression learning apparatus and method, facial …
JR Movellan, MS Bartlett, GC Littlewort, J Hershey, IR Fasel, EC Carlson, ...
US Patent 7,379,568, 2008
1552008
Attention-based multimodal fusion for video description
C Hori, T Hori, TY Lee, Z Zhang, B Harsham, JR Hershey, TK Marks, ...
Proceedings of the IEEE international conference on computer vision, 4193-4202, 2017
1422017
Improved mvdr beamforming using single-channel mask prediction networks.
H Erdogan, JR Hershey, S Watanabe, MI Mandel, J Le Roux
Interspeech, 1981-1985, 2016
1382016
Hybrid CTC/attention architecture for end-to-end speech recognition
S Watanabe, T Hori, S Kim, JR Hershey, T Hayashi
IEEE Journal of Selected Topics in Signal Processing 11 (8), 1240-1253, 2017
1322017
Full-capacity unitary recurrent neural networks
S Wisdom, T Powers, J Hershey, J Le Roux, L Atlas
Advances in Neural Information Processing Systems, 4880-4888, 2016
1322016
Super-human multi-talker speech recognition: The IBM 2006 speech separation challenge system
T Kristjansson, J Hershey, P Olsen, S Rennie, R Gopinath
Ninth International Conference on Spoken Language Processing, 2006
1202006
Single microphone source separation using high resolution signal reconstruction
T Kristjansson, H Attias, J Hershey
2004 IEEE International Conference on Acoustics, Speech, and Signal …, 2004
1062004
Deep beamforming networks for multi-channel speech recognition
X Xiao, S Watanabe, H Erdogan, L Lu, J Hershey, ML Seltzer, G Chen, ...
2016 IEEE International Conference on Acoustics, Speech and Signal …, 2016
1012016
Deep clustering and conventional networks for music separation: Stronger together
Y Luo, Z Chen, JR Hershey, J Le Roux, N Mesgarani
2017 IEEE International Conference on Acoustics, Speech and Signal …, 2017
992017
Speech enhancement and recognition using multi-task learning of long short-term memory recurrent neural networks
Z Chen, S Watanabe, H Erdogan, JR Hershey
Sixteenth Annual Conference of the International Speech Communication …, 2015
932015
The system can't perform the operation now. Try again later.
Articles 1–20