Publications

314 / 3,604 publications found.


  •  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}
    • }
  •  Kanagawa, H., Tachioka, Y., Watanabe, S., Ishii, J., "Feature-Space Structural MAPLR with Regression Tree-Based Multiple Transformation Matrices for DNN", Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), DOI: 10.1109/​APSIPA.2015.7415425, December 2015, pp. 86-92.
    BibTeX TR2015-150 PDF
    • @inproceedings{Kanagawa2015dec,
    • author = {Kanagawa, H. and Tachioka, Y. and Watanabe, S. and Ishii, J.},
    • title = {Feature-Space Structural MAPLR with Regression Tree-Based Multiple Transformation Matrices for DNN},
    • booktitle = {Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)},
    • year = 2015,
    • pages = {86--92},
    • month = dec,
    • doi = {10.1109/APSIPA.2015.7415425},
    • url = {https://www.merl.com/publications/TR2015-150}
    • }
  •  Barker, J., Marxer, R., Vincent, E., Watanabe, S., "The Third 'CHiME' Speech Separation and Recognition Challenge: Dataset, Task and Baselines", IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), DOI: 10.1109/​ASRU.2015.75404837, December 2015, pp. 504-511.
    BibTeX TR2015-136 PDF
    • @inproceedings{Barker2015dec,
    • author = {Barker, J. and Marxer, R. and Vincent, E. and Watanabe, S.},
    • title = {The Third 'CHiME' Speech Separation and Recognition Challenge: Dataset, Task and Baselines},
    • booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)},
    • year = 2015,
    • pages = {504--511},
    • month = dec,
    • publisher = {IEEE},
    • doi = {10.1109/ASRU.2015.75404837},
    • url = {https://www.merl.com/publications/TR2015-136}
    • }
  •  Hsiao, R., Ma, J., Hartmann, W., Karafiat, M., Grezl, F., Burget, L., Szoke, I., Cernocky, J., Watanabe, S., Chen, Z., Mallidi, S.H., Hermansky, H., Tsakalidis, S., Schwartz, R., "Robust Speech Recognition in Unknown Reverberant and Noisy Conditions", IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), DOI: 10.1109/​ARSU.2015.7404841, December 2015, pp. 533-538.
    BibTeX TR2015-138 PDF
    • @inproceedings{Hsiao2015dec,
    • author = {Hsiao, R. and Ma, J. and Hartmann, W. and Karafiat, M. and Grezl, F. and Burget, L. and Szoke, I. and Cernocky, J. and Watanabe, S. and Chen, Z. and Mallidi, S.H. and Hermansky, H. and Tsakalidis, S. and Schwartz, R.},
    • title = {Robust Speech Recognition in Unknown Reverberant and Noisy Conditions},
    • booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)},
    • year = 2015,
    • pages = {533--538},
    • month = dec,
    • publisher = {IEEE},
    • doi = {10.1109/ARSU.2015.7404841},
    • url = {https://www.merl.com/publications/TR2015-138}
    • }
  •  Moriya, T., Shinozaki, T., Watanabe, S., Duh, K., "Automation of System Building for State-of-the-Art Large Vocabulary Speech Recognition Using Evolution Strategy", IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), DOI: 10.1109/​ASRU.2015.7404852, December 2015, pp. 610-616.
    BibTeX TR2015-137 PDF
    • @inproceedings{Moriya2015dec,
    • author = {Moriya, T. and Shinozaki, T. and Watanabe, S. and Duh, K.},
    • title = {Automation of System Building for State-of-the-Art Large Vocabulary Speech Recognition Using Evolution Strategy},
    • booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)},
    • year = 2015,
    • pages = {610--616},
    • month = dec,
    • doi = {10.1109/ASRU.2015.7404852},
    • url = {https://www.merl.com/publications/TR2015-137}
    • }
  •  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}
    • }
  •  Tawara, N., Ogawa, T., Watanabe, S., Nakamura, A., Kobayashi, T., "A Sampling-Based Speaker Clustering Using Utterance-Oriented Dirichlet Process Mixture Model and Its Evaluation on Large Scale Data", APSIPA Transactions on Signal and Information Processing, DOI: 10.1017/​ATSIP.2015.19, Vol. 4, October 2015.
    BibTeX TR2015-153 PDF
    • @article{Tawara2015oct,
    • author = {Tawara, N. and Ogawa, T. and Watanabe, S. and Nakamura, A. and Kobayashi, T.},
    • title = {A Sampling-Based Speaker Clustering Using Utterance-Oriented Dirichlet Process Mixture Model and Its Evaluation on Large Scale Data},
    • journal = {APSIPA Transactions on Signal and Information Processing},
    • year = 2015,
    • volume = 4,
    • month = oct,
    • doi = {10.1017/ATSIP.2015.19},
    • issn = {2048-7703},
    • url = {https://www.merl.com/publications/TR2015-153}
    • }
  •  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}
    • }
  •  Luan, Y., Watanabe, S., Harsham, B.A., "Efficient Learning for Spoken Language Understanding Tasks with Word Embedding Based Pre-Training", Interspeech, September 2015, vol. 1 or 5, pp. 1398-1402.
    BibTeX TR2015-097 PDF
    • @inproceedings{Luan2015sep,
    • author = {Luan, Y. and Watanabe, S. and Harsham, B.A.},
    • title = {Efficient Learning for Spoken Language Understanding Tasks with Word Embedding Based Pre-Training},
    • booktitle = {Interspeech},
    • year = 2015,
    • volume = {1 or 5},
    • pages = {1398--1402},
    • month = sep,
    • isbn = {978-1-5108-1790-6},
    • url = {https://www.merl.com/publications/TR2015-097}
    • }
  •  Tachioka, Y., Watanabe, S., "Uncertainty Training and Decoding Methods of Deep Neural Networks Based on Stochastic Representation of Enhanced Features", Interspeech, September 2015, vol. 1 or 5, pp. 3541.
    BibTeX TR2015-099 PDF
    • @inproceedings{Tachioka2015sep,
    • author = {Tachioka, Y. and Watanabe, S.},
    • title = {Uncertainty Training and Decoding Methods of Deep Neural Networks Based on Stochastic Representation of Enhanced Features},
    • booktitle = {Interspeech},
    • year = 2015,
    • volume = {1 or 5},
    • pages = 3541,
    • month = sep,
    • isbn = {978-1-5108-1790-6},
    • url = {https://www.merl.com/publications/TR2015-099}
    • }
  •  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}
    • }
  •  Tachioka, Y., Narita, T., Watanabe, S., "Effectiveness of Dereverberation, Feature Transformation, Discriminative Training Methods, and System Combination Approach for Various Reverberant Environments", EURASIP Journal on Advances in Signal Processing, DOI: 10.1186/​s13634-015-0241-y, June 2015.
    BibTeX TR2015-152 PDF
    • @article{Tachioka2015jun,
    • author = {Tachioka, Y. and Narita, T. and Watanabe, S.},
    • title = {Effectiveness of Dereverberation, Feature Transformation, Discriminative Training Methods, and System Combination Approach for Various Reverberant Environments},
    • journal = {EURASIP Journal on Advances in Signal Processing},
    • year = 2015,
    • month = jun,
    • doi = {10.1186/s13634-015-0241-y},
    • url = {https://www.merl.com/publications/TR2015-152}
    • }
  •  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}
    • }
  •  Shinozaki, T., Watanabe, S., "Structure Discovery of Deep Neural Network Based on Evolutionary Algorithms", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2015.7178918, April 2015, pp. 4979-4983.
    BibTeX TR2015-032 PDF
    • @inproceedings{Shinozaki2015apr,
    • author = {Shinozaki, T. and Watanabe, S.},
    • title = {Structure Discovery of Deep Neural Network Based on Evolutionary Algorithms},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2015,
    • pages = {4979--4983},
    • month = apr,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP.2015.7178918},
    • url = {https://www.merl.com/publications/TR2015-032}
    • }
  •  Tachioka, Y., Watanabe, S., "Discriminative Method for Recurrent Neural Network Language Models", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2015.7179000, April 2015, pp. 5386-5390.
    BibTeX TR2015-033 PDF
    • @inproceedings{Tachioka2015apr,
    • author = {Tachioka, Y. and Watanabe, S.},
    • title = {Discriminative Method for Recurrent Neural Network Language Models},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2015,
    • pages = {5386--5390},
    • month = apr,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP.2015.7179000},
    • url = {https://www.merl.com/publications/TR2015-033}
    • }
  •  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}
    • }
  •  Gerkmann, T., Krawczyk, M., Le Roux, J., "Phase Processing for Single Channel Speech Enhancement: History and Recent Advances", IEEE Signal Processing Magazine, DOI: 10.1109/​MSP.2014.2369251, Vol. 32, No. 2, pp. 55-66, March 2015.
    BibTeX TR2014-122 PDF
    • @article{Gerkmann2015mar,
    • author = {Gerkmann, T. and Krawczyk, M. and {Le Roux}, J.},
    • title = {Phase Processing for Single Channel Speech Enhancement: History and Recent Advances},
    • journal = {IEEE Signal Processing Magazine},
    • year = 2015,
    • volume = 32,
    • number = 2,
    • pages = {55--66},
    • month = mar,
    • publisher = {IEEE},
    • doi = {10.1109/MSP.2014.2369251},
    • issn = {1053-5888},
    • url = {https://www.merl.com/publications/TR2014-122}
    • }
  •  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}
    • }
  •  Tachioka, Y., Watanabe, S., Le Roux, J., Hershey, J.R., "Sequential Maximum Mutual Information Linear Discriminant Analysis for Speech Recognition", Interspeech, September 2014, vol. 15, pp. 2415-2419.
    BibTeX TR2014-079 PDF
    • @inproceedings{Tachioka2014sep,
    • author = {Tachioka, Y. and Watanabe, S. and {Le Roux}, J. and Hershey, J.R.},
    • title = {Sequential Maximum Mutual Information Linear Discriminant Analysis for Speech Recognition},
    • booktitle = {Interspeech},
    • year = 2014,
    • volume = 15,
    • pages = {2415--2419},
    • month = sep,
    • publisher = {International Speech Communication Association},
    • issn = {2308-457X},
    • url = {https://www.merl.com/publications/TR2014-079}
    • }