Publications

196 / 2,468 publications found.


  •  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 Download PDFRead TR2016-011
    • @inproceedings{Hori2016mar,
    • author = {Hori, T. and Hori, C. and Watanabe, S. and Hershey, J.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 = {http://www.merl.com/publications/TR2016-011}
    • }
  •  Vesely, K.; Watanabe, S.; Zmolikova, K.; Karafiat, M.; Burget, L.; Cernocky, J.H., "Sequence Summarizing Neural Network for Speaker Adaptation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2016.7472692, March 2016, pp. 5315-5319.
    BibTeX Download PDFRead TR2016-001
    • @inproceedings{Vesely2016mar,
    • author = {Vesely, K. and Watanabe, S. and Zmolikova, K. and Karafiat, M. and Burget, L. and Cernocky, J.H.},
    • title = {Sequence Summarizing Neural Network for Speaker Adaptation},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2016,
    • pages = {5315--5319},
    • month = mar,
    • doi = {10.1109/ICASSP.2016.7472692},
    • url = {http://www.merl.com/publications/TR2016-001}
    • }
  •  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 Download PDFRead TR2016-008
    • @inproceedings{Wisdom2016mar,
    • author = {Wisdom, S. and Hershey, J.R. and {Le Roux}, J. and Watanabe, S.},
    • 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 = {http://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 Download PDFRead TR2016-002
    • @inproceedings{Xiao2016mar,
    • author = {Xiao, X. and Watanabe, S. and Erdogan, H. and Lu, L. and Hershey, J. and Seltzer, M. and Chen, G. and Zhang, Y. and Mandel, M. and Yu, D.},
    • 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 = {http://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), DOI: 10.1109/APSIPA.2015.7415425, December 2015, pp. 86-92.
    BibTeX Download PDFRead TR2015-150
    • @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)},
    • year = 2015,
    • pages = {86--92},
    • month = dec,
    • doi = {10.1109/APSIPA.2015.7415425},
    • url = {http://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 Download PDFRead TR2015-136
    • @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 = {http://www.merl.com/publications/TR2015-136}
    • }
  •  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 Download PDFRead TR2015-135
    • @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 = {http://www.merl.com/publications/TR2015-135}
    • }
  •  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 Download PDFRead TR2015-138
    • @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 = {http://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 Download PDFRead TR2015-137
    • @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 = {http://www.merl.com/publications/TR2015-137}
    • }
  •  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 Download PDFRead TR2015-134
    • @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 = {http://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, ISSN: 2048-7703, Vol. 4, October 2015.
    BibTeX Download PDFRead TR2015-153
    • @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 = {http://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, October 2015.
    BibTeX Download PDFRead TR2015-120
    • @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},
    • year = 2015,
    • month = oct,
    • url = {http://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, ISBN: 978-1-5108-1790-6, September 2015, vol. 1 or 5, pp. 3561.
    BibTeX Download PDFRead TR2015-098
    • @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 = {http://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, ISBN: 978-1-5108-1790-6, September 2015, vol. 1 of 5, pp. 1278.
    BibTeX Download PDFRead TR2015-100
    • @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 = {http://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, ISBN: 978-1-5108-1790-6, September 2015, vol. 1 or 5, pp. 1398-1402.
    BibTeX Download PDFRead TR2015-097
    • @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 = {http://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, ISBN: 978-1-5108-1790-6, September 2015, vol. 1 or 5, pp. 3541.
    BibTeX Download PDFRead TR2015-099
    • @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 = {http://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, ISBN: 978-3-319-22482-4, August 2015, vol. 9237, pp. 91-99.
    BibTeX Download PDFRead TR2015-094
    • @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 = {http://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 Download PDFRead TR2015-152
    • @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 = {http://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 Download PDFRead TR2015-031
    • @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 = {http://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 Download PDFRead TR2015-029
    • @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 = {http://www.merl.com/publications/TR2015-029}
    • }