- Hori, T., Watanabe, S., Hershey, J.R., "Joint CTC/attention decoding for end-to-end speech recognition", Association for Computational Linguistics (ACL), DOI: 10.18653/v1/P17-1048, July 2017, pp. 518-529.
BibTeX TR2017-103 PDF Video- @inproceedings{Hori2017jul,
- author = {Hori, Takaaki and Watanabe, Shinji and Hershey, John R.},
- title = {{Joint CTC/attention decoding for end-to-end speech recognition}},
- booktitle = {Association for Computational Linguistics (ACL)},
- year = 2017,
- pages = {518--529},
- month = jul,
- doi = {10.18653/v1/P17-1048},
- url = {https://www.merl.com/publications/TR2017-103}
- }
- Luo, Y., Chen, Z., Hershey, J.R., Le Roux, J., Mesgarani, N., "Deep Clustering and Conventional Networks for Music Separation: Strong Together", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
BibTeX TR2017-010 PDF- @inproceedings{Luo2017mar,
- author = {Luo, Yi and Chen, Zhuo and Hershey, John R. and {Le Roux}, Jonathan and Mesgarani, Nima},
- title = {{Deep Clustering and Conventional Networks for Music Separation: Strong Together}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2017,
- month = mar,
- url = {https://www.merl.com/publications/TR2017-010}
- }
- Meng, Z., Watanabe, S., Hershey, J.R., Erdogan, H., "Deep Long Short-Term Memory Adaptive Beamforming Networks for Multichannel Robust Speech Recognition", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
BibTeX TR2017-012 PDF- @inproceedings{Meng2017mar,
- author = {Meng, Zhong and Watanabe, Shinji and Hershey, John R. and Erdogan, Hakan},
- title = {{Deep Long Short-Term Memory Adaptive Beamforming Networks for Multichannel Robust Speech Recognition}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2017,
- month = mar,
- url = {https://www.merl.com/publications/TR2017-012}
- }
- Watanabe, S., Hori, T., Le Roux, J., Hershey, J.R., "Student-Teacher Network Learning with Enhanced Features", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
BibTeX TR2017-011 PDF- @inproceedings{Watanabe2017mar,
- author = {Watanabe, Shinji and Hori, Takaaki and {Le Roux}, Jonathan and Hershey, John R.},
- title = {{Student- Teacher Network Learning with Enhanced Features}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2017,
- month = mar,
- url = {https://www.merl.com/publications/TR2017-011}
- }
- Hori, T., Wang, H., Hori, C., Watanabe, S., Harsham, B.A., Le Roux, J., Hershey, J.R., Koji, Y., Jing, Y., Zhu, Z., Aikawa, T., "Dialog State Tracking with Attention-based Sequence-to-sequence Learning", IEEE Workshop on Spoken Language Technology (SLT), DOI: 10.1109/SLT.2016.7846317, December 2016, pp. 552-558.
BibTeX TR2016-163 PDF- @inproceedings{Hori2016dec,
- author = {Hori, Takaaki and Wang, Hai and Hori, Chiori and Watanabe, Shinji and Harsham, Bret A. and {Le Roux}, Jonathan and Hershey, John R. and Koji, Yusuke and Jing, Yi and Zhu, Zhaocheng and Aikawa, Takeyuki},
- title = {{Dialog State Tracking with Attention-based Sequence-to-sequence Learning}},
- booktitle = {IEEE Workshop on Spoken Language Technology (SLT)},
- year = 2016,
- pages = {552--558},
- month = dec,
- doi = {10.1109/SLT.2016.7846317},
- url = {https://www.merl.com/publications/TR2016-163}
- }
- Wisdom, S., Powers, T., Hershey, J.R., Le Roux, J., Atlas, L., "Full-Capacity Unitary Recurrent Neural Networks", Advances in Neural Information Processing Systems (NIPS), December 2016.
BibTeX TR2016-155 PDF- @inproceedings{Wisdom2016dec,
- author = {Wisdom, Scott and Powers, Thomas and Hershey, John R. and {Le Roux}, Jonathan and Atlas, Les},
- title = {{Full-Capacity Unitary Recurrent Neural Networks}},
- booktitle = {Advances in Neural Information Processing Systems (NIPS)},
- year = 2016,
- month = dec,
- url = {https://www.merl.com/publications/TR2016-155}
- }
- Erdogan, H., Hershey, J.R., Watanabe, S., Mandel, M., Le Roux, J., "Improved MVDR beamforming using single-channel mask prediction networks", Interspeech, DOI: 10.21437/Interspeech.2016-552, September 2016, pp. 1981-1985.
BibTeX TR2016-072 PDF- @inproceedings{Erdogan2016sep,
- author = {Erdogan, Hakan and Hershey, John R. and Watanabe, Shinji and Mandel, Michael and {Le Roux}, Jonathan},
- title = {{Improved MVDR beamforming using single-channel mask prediction networks}},
- booktitle = {Interspeech},
- year = 2016,
- pages = {1981--1985},
- month = sep,
- doi = {10.21437/Interspeech.2016-552},
- url = {https://www.merl.com/publications/TR2016-072}
- }
- Hori, C., Hori, T., Watanabe, S., Hershey, J.R., "Context-Sensitive and Role-Dependent Spoken Language Understanding using Bidirectional and Attention LSTMs", Interspeech, DOI: 10.21437/Interspeech.2016-1171, September 2016, pp. 3236-3240.
BibTeX TR2016-074 PDF- @inproceedings{Hori2016sep,
- author = {Hori, Chiori and Hori, Takaaki and Watanabe, Shinji and Hershey, John R.},
- title = {{Context-Sensitive and Role-Dependent Spoken Language Understanding using Bidirectional and Attention LSTMs}},
- booktitle = {Interspeech},
- year = 2016,
- pages = {3236--3240},
- month = sep,
- doi = {10.21437/Interspeech.2016-1171},
- url = {https://www.merl.com/publications/TR2016-074}
- }
- Isik, Y., Le Roux, J., Chen, Z., Watanabe, S., Hershey, J.R., "Single-Channel Multi-Speaker Separation using Deep Clustering", Interspeech, DOI: 10.21437/Interspeech.2016-1176, September 2016, pp. 545-549.
BibTeX TR2016-073 PDF- @inproceedings{Isik2016sep,
- author = {Isik, Yusuf and {Le Roux}, Jonathan and Chen, Zhuo and Watanabe, Shinji and Hershey, John R.},
- title = {{Single-Channel Multi-Speaker Separation using Deep Clustering}},
- booktitle = {Interspeech},
- year = 2016,
- pages = {545--549},
- month = sep,
- doi = {10.21437/Interspeech.2016-1176},
- url = {https://www.merl.com/publications/TR2016-073}
- }
- Hori, C., Watanabe, S., Hori, T., Harsham, B.A., Hershey, J.R., Koji, Y., Fujii, Y., Furumoto, Y., "Driver Confusion Status Detection Using Recurrent Neural Networks", IEEE International Conference on Multimedia and Expo (ICME), DOI: 10.1109/ICME.2016.7552966, July 2016.
BibTeX TR2016-088 PDF- @inproceedings{Hori2016jul,
- author = {Hori, Chiori and Watanabe, Shinji and Hori, Takaaki and Harsham, Bret A. and Hershey, John R. and Koji, Yusuke and Fujii, Youichi and Furumoto, Yuki},
- title = {{Driver Confusion Status Detection Using Recurrent Neural Networks}},
- booktitle = {IEEE International Conference on Multimedia and Expo (ICME)},
- year = 2016,
- month = jul,
- doi = {10.1109/ICME.2016.7552966},
- url = {https://www.merl.com/publications/TR2016-088}
- }
- Hershey, J.R., Chen, Z., Le Roux, J., Watanabe, S., "Deep Clustering: Discriminative Embeddings for Segmentation and Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2016.7471631, March 2016, pp. 31-35.
BibTeX TR2016-003 PDF- @inproceedings{Hershey2016mar,
- author = {Hershey, John R. and Chen, Zhuo and {Le Roux}, Jonathan and Watanabe, Shinji},
- title = {{Deep Clustering: Discriminative Embeddings for Segmentation and Separation}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2016,
- pages = {31--35},
- month = mar,
- doi = {10.1109/ICASSP.2016.7471631},
- url = {https://www.merl.com/publications/TR2016-003}
- }
- Hori, T., Hori, C., Watanabe, S., Hershey, J.R., "Minimum Word Error Training of Long Short-Term Memory Recurrent Neural Network Language Models for Speech Recognition", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2016.7472827, March 2016, pp. 5990-5994.
BibTeX TR2016-011 PDF- @inproceedings{Hori2016mar,
- author = {Hori, Takaaki and Hori, Chiori and Watanabe, Shinji and Hershey, John R.},
- title = {{Minimum Word Error Training of Long Short-Term Memory Recurrent Neural Network Language Models for Speech Recognition}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2016,
- pages = {5990--5994},
- month = mar,
- doi = {10.1109/ICASSP.2016.7472827},
- url = {https://www.merl.com/publications/TR2016-011}
- }
- Wisdom, S., Hershey, J.R., Le Roux, J., Watanabe, S., "Deep Unfolding for Multichannel Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2016.7471649, March 2016, pp. 121-125.
BibTeX TR2016-008 PDF- @inproceedings{Wisdom2016mar,
- author = {Wisdom, Scott and Hershey, John R. and {Le Roux}, Jonathan and Watanabe, Shinji},
- title = {{Deep Unfolding for Multichannel Source Separation}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2016,
- pages = {121--125},
- month = mar,
- doi = {10.1109/ICASSP.2016.7471649},
- url = {https://www.merl.com/publications/TR2016-008}
- }
- Xiao, X., Watanabe, S., Erdogan, H., Lu, L., Hershey, J., Seltzer, M., Chen, G., Zhang, Y., Mandel, M., Yu, D., "Deep Beamforming Networks for Multi-Channel Speech Recognition", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2016.7472778, March 2016, pp. 5745-5749.
BibTeX TR2016-002 PDF- @inproceedings{Xiao2016mar,
- author = {Xiao, Xiong and Watanabe, Shinji and Erdogan, Hakan and Lu, Liang and Hershey, John and Seltzer, Mike and Chen, Guoguo and Zhang, Yu and Mandel, Michael and Yu, Dong},
- title = {{Deep Beamforming Networks for Multi-Channel Speech Recognition}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2016,
- pages = {5745--5749},
- month = mar,
- doi = {10.1109/ICASSP.2016.7472778},
- url = {https://www.merl.com/publications/TR2016-002}
- }
- Hori, T., Chen, Z., Erdogan, H., Hershey, J.R., Le Roux, J., Mitra, V., Watanabe, S., "The MERL/SRI System for the 3rd CHiME Challenge Using Beamforming, Robust Feature Extraction, and Advanced Speech Recognition", IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), DOI: 10.1109/ASRU.2015.7404833, December 2015, pp. 475-481.
BibTeX TR2015-135 PDF- @inproceedings{Hori2015dec2,
- author = {Hori, T. and Chen, Z. and Erdogan, H. and Hershey, J.R. and {Le Roux}, J. and Mitra, V. and Watanabe, S.},
- title = {{The MERL/SRI System for the 3rd CHiME Challenge Using Beamforming, Robust Feature Extraction, and Advanced Speech Recognition}},
- booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)},
- year = 2015,
- pages = {475--481},
- month = dec,
- publisher = {IEEE},
- doi = {10.1109/ASRU.2015.7404833},
- url = {https://www.merl.com/publications/TR2015-135}
- }
- Hori, C.., Hori, T., Watanabe, S., Hershey, J.R., "Context Sensitive Spoken Language Understanding Using Role Dependent LSTM Layers", NIPS Workshop on Machine Learning for Spoken Language Understanding and Interaction, December 2015.
BibTeX TR2015-134 PDF- @inproceedings{Hori2015dec1,
- author = {Hori, C. and Hori, T. and Watanabe, S. and Hershey, J.R.},
- title = {{Context Sensitive Spoken Language Understanding Using Role Dependent LSTM Layers}},
- booktitle = {NIPS Workshop on Machine Learning for Spoken Language Understanding and Interaction},
- year = 2015,
- month = dec,
- url = {https://www.merl.com/publications/TR2015-134}
- }
- Harsham, B.A., Watanabe, S., Esenther, A., Hershey, J.R., Le Roux, J., Luan, Y., Nikovski, D.N., Potluru, V.K., "Driver Prediction to Improve Interaction with In-Vehicle HMI", Workshop on DSP for In-Vehicle Systems and Safety (DSP), October 2015.
BibTeX TR2015-120 PDF- @inproceedings{Harsham2015oct,
- author = {Harsham, B.A. and Watanabe, S. and Esenther, A. and Hershey, J.R. and {Le Roux}, J. and Luan, Y. and Nikovski, D.N. and Potluru, V.K.},
- title = {{Driver Prediction to Improve Interaction with In-Vehicle HMI}},
- booktitle = {Workshop on DSP for In-Vehicle Systems and Safety (DSP)},
- year = 2015,
- month = oct,
- url = {https://www.merl.com/publications/TR2015-120}
- }
- Abdelaziz, A.H., Watanabe, S., Hershey, J.R., Vincent, E., Kolossa, D., "Uncertainty Propagation Through Deep Neural Networks", Interspeech, September 2015, vol. 1 or 5, pp. 3561.
BibTeX TR2015-098 PDF- @inproceedings{Abdelaziz2015sep,
- author = {Abdelaziz, A.H. and Watanabe, S. and Hershey, J.R. and Vincent, E. and Kolossa, D.},
- title = {{Uncertainty Propagation Through Deep Neural Networks}},
- booktitle = {Interspeech},
- year = 2015,
- volume = {1 or 5},
- pages = 3561,
- month = sep,
- isbn = {978-1-5108-1790-6},
- url = {https://www.merl.com/publications/TR2015-098}
- }
- Chen, Z., Watanabe, S., Erdogan, H., Hershey, J.R., "Speech Enhancement and Recognition Using Multi-Task Learning of Long Short-Term Memory Recurrent Neural Networks", Interspeech, September 2015, vol. 1 of 5, pp. 1278.
BibTeX TR2015-100 PDF- @inproceedings{Chen2015sep,
- author = {Chen, Z. and Watanabe, S. and Erdogan, H. and Hershey, J.R.},
- title = {{Speech Enhancement and Recognition Using Multi-Task Learning of Long Short-Term Memory Recurrent Neural Networks}},
- booktitle = {Interspeech},
- year = 2015,
- volume = {1 of 5},
- pages = 1278,
- month = sep,
- isbn = {978-1-5108-1790-6},
- url = {https://www.merl.com/publications/TR2015-100}
- }
- Weninger, F.J., Erdogan, H., Watanabe, S., Vincent, E., Le Roux, J., Hershey, J.R., Schuller, B.W., "Speech Enhancement with LSTM Recurrent Neural Networks and Its Application to Noise-Robust ASR", Latent Variable Analysis and Signal Separation Conference (LVA), DOI: 10.1007/978-3-319-22482-4_11, August 2015, vol. 9237, pp. 91-99.
BibTeX TR2015-094 PDF- @inproceedings{Weninger2015aug,
- author = {Weninger, F.J. and Erdogan, H. and Watanabe, S. and Vincent, E. and {Le Roux}, J. and Hershey, J.R. and Schuller, B.W.},
- title = {{Speech Enhancement with LSTM Recurrent Neural Networks and Its Application to Noise-Robust ASR}},
- booktitle = {Latent Variable Analysis and Signal Separation Conference (LVA)},
- year = 2015,
- volume = 9237,
- pages = {91--99},
- month = aug,
- doi = {10.1007/978-3-319-22482-4_11},
- isbn = {978-3-319-22482-4},
- url = {https://www.merl.com/publications/TR2015-094}
- }
- Erdogan, H., Hershey, J.R., Watanabe, S., Le Roux, J., "Phase-Sensitive and Recognition-Boosted Speech Separation Using Deep Recurrent Neural Networks", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2015.7178061, April 2015, pp. 708-712.
BibTeX TR2015-031 PDF- @inproceedings{Erdogan2015apr,
- author = {Erdogan, H. and Hershey, J.R. and Watanabe, S. and {Le Roux}, J.},
- title = {{Phase-Sensitive and Recognition-Boosted Speech Separation Using Deep Recurrent Neural Networks}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2015,
- pages = {708--712},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP.2015.7178061},
- url = {https://www.merl.com/publications/TR2015-031}
- }
- Le Roux, J., Hershey, J.R., Weninger, F.J., "Deep NMF for Speech Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2015.7177933, April 2015, pp. 66-70.
BibTeX TR2015-029 PDF- @inproceedings{LeRoux2015apr1,
- author = {{Le Roux}, J. and Hershey, J.R. and Weninger, F.J.},
- title = {{Deep NMF for Speech Separation}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2015,
- pages = {66--70},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP.2015.7177933},
- url = {https://www.merl.com/publications/TR2015-029}
- }
- Le Roux, J., Vincent, E., Hershey, J.R., Ellis, D.P.W., "Micbots: Collecting Large Realistic Datasets for Speech and Audio Research Using Mobile Robots", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2015.7179050, April 2015, pp. 5635-5639.
BibTeX TR2015-030 PDF- @inproceedings{LeRoux2015apr2,
- author = {{Le Roux}, J. and Vincent, E. and Hershey, J.R. and Ellis, D.P.W.},
- title = {{Micbots: Collecting Large Realistic Datasets for Speech and Audio Research Using Mobile Robots}},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2015,
- pages = {5635--5639},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP.2015.7179050},
- url = {https://www.merl.com/publications/TR2015-030}
- }
- Le Roux, J., Weninger, F.J., Hershey, J.R., "Sparse NMF -- half-baked or well done?," Tech. Rep. TR2015-023, Mitsubishi Electric Research Laboratories, March 2015.
BibTeX TR2015-023 PDF- @techreport{LeRoux2015mar,
- author = {{Le Roux}, J. and Weninger, F.J. and Hershey, J.R.},
- title = {{Sparse NMF -- half-baked or well done?}},
- institution = {Mitsubishi Electric Research Laboratories},
- year = 2015,
- number = {TR2015-023},
- address = {Cambridge MA, USA},
- month = mar,
- url = {https://www.merl.com/publications/TR2015-023}
- }
- Weninger, F., Le Roux, J., Hershey, J.R., Schuller, B., "Discriminatively Trained Recurrent Neural Networks for Single-Channel Speech Separation", IEEE Global Conference on Signal and Information Processing (GlobalSIP), DOI: 10.1109/GlobalSIP.2014.7032183, December 2014, pp. 577-581.
BibTeX TR2014-104 PDF- @inproceedings{Weninger2014dec,
- author = {Weninger, F. and {Le Roux}, J. and Hershey, J.R. and Schuller, B.},
- title = {{Discriminatively Trained Recurrent Neural Networks for Single-Channel Speech Separation}},
- booktitle = {IEEE Global Conference on Signal and Information Processing (GlobalSIP)},
- year = 2014,
- pages = {577--581},
- month = dec,
- publisher = {IEEE},
- doi = {10.1109/GlobalSIP.2014.7032183},
- url = {https://www.merl.com/publications/TR2014-104}
- }