Publications

52 / 2,509 publications found.


  •  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}
    • }
  •  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}
    • }
  •  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}
    • }
  •  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}
    • }
  •  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}
    • }
  •  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}
    • }
  •  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 Download PDFRead TR2015-030
    • @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 = {http://www.merl.com/publications/TR2015-030}
    • }
  •  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 Download PDFRead TR2014-104
    • @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 = {http://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, ISSN: 2308-457X, September 2014, vol. 15, pp. 2415-2419.
    BibTeX Download PDFRead TR2014-079
    • @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 = {http://www.merl.com/publications/TR2014-079}
    • }
  •  Watanabe, S.; Hershey, J.R.; Marks, T.K.; Fujii, Y.; Koji, Y., "Cost-level integration of statistical and rule-based dialog managers", Interspeech, ISSN: 308-457X, September 2014, vol. 15, pp. 323-327.
    BibTeX Download PDFRead TR2014-082
    • @inproceedings{Watanabe2014sep,
    • author = {Watanabe, S. and Hershey, J.R. and Marks, T.K. and Fujii, Y. and Koji, Y.},
    • title = {Cost-level integration of statistical and rule-based dialog managers},
    • booktitle = {Interspeech},
    • year = 2014,
    • volume = 15,
    • pages = {323--327},
    • month = sep,
    • publisher = {International Speech Communication Association},
    • issn = {308-457X},
    • url = {http://www.merl.com/publications/TR2014-082}
    • }
  •  Weninger, F.; Le Roux, J.; Hershey, J.R.; Watanabe, S., "Discriminative NMF and its application to single-channel source separation", Interspeech, ISSN: 2308-457X, September 2014, vol. 15, pp. 865-869.
    BibTeX Download PDFRead TR2014-081
    • @inproceedings{Weninger2014sep,
    • author = {Weninger, F. and {Le Roux}, J. and Hershey, J.R. and Watanabe, S.},
    • title = {Discriminative NMF and its application to single-channel source separation},
    • booktitle = {Interspeech},
    • year = 2014,
    • volume = 15,
    • pages = {865--869},
    • month = sep,
    • publisher = {International Speech Communication Association},
    • issn = {2308-457X},
    • url = {http://www.merl.com/publications/TR2014-081}
    • }
  •  Hershey, J.R.; Le Roux, J.; Weninger, F., "Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures," Tech. Rep. TR2014-117, arXiv, August 2014.
    BibTeX Download PDFRead TR2014-117
    • @techreport{Hershey2014aug,
    • author = {Hershey, J.R. and {Le Roux}, J. and Weninger, F.},
    • title = {Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures},
    • journal = {arXiv},
    • year = 2014,
    • month = aug,
    • url = {http://www.merl.com/publications/TR2014-117}
    • }
  •  Weninger, F.; Watanabe, S.; Le Roux, J.; Hershey, J.R.; Tachioka, Y.; Geiger, J.; Schuller, B.; Rigoll, G., "The MERL/MELCO/TUM System for the REVERB Challenge Using Deep Recurrent Neural Network Feature Enhancement", IEEE REVERB Workshop, May 2014.
    BibTeX Download PDFRead TR2014-033
    • @inproceedings{Weninger2014may2,
    • author = {Weninger, F. and Watanabe, S. and {Le Roux}, J. and Hershey, J.R. and Tachioka, Y. and Geiger, J. and Schuller, B. and Rigoll, G.},
    • title = {The MERL/MELCO/TUM System for the REVERB Challenge Using Deep Recurrent Neural Network Feature Enhancement},
    • booktitle = {IEEE REVERB Workshop},
    • year = 2014,
    • month = may,
    • url = {http://www.merl.com/publications/TR2014-033}
    • }
  •  Simsekli, U.; Le Roux, J.; Hershey, J.R., "Non-negative Source-filter Dynamical System for Speech Enhancement", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2014.6854797, May 2014, pp. 6206-6210.
    BibTeX Download PDFRead TR2014-027
    • @inproceedings{Simsekli2014may,
    • author = {Simsekli, U. and {Le Roux}, J. and Hershey, J.R.},
    • title = {Non-negative Source-filter Dynamical System for Speech Enhancement},
    • booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
    • year = 2014,
    • pages = {6206--6210},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP.2014.6854797},
    • url = {http://www.merl.com/publications/TR2014-027}
    • }
  •  Tang, H.; Watanabe, S.; Marks, T.K.; Hershey, J.R., "Log-linear Dialog Manager", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2014.6854371, May 2014, pp. 4092-4096.
    BibTeX Download PDFRead TR2014-024
    • @inproceedings{Tang2014may,
    • author = {Tang, H. and Watanabe, S. and Marks, T.K. and Hershey, J.R.},
    • title = {Log-linear Dialog Manager},
    • booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
    • year = 2014,
    • pages = {4092--4096},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP.2014.6854371},
    • url = {http://www.merl.com/publications/TR2014-024}
    • }
  •  Tachioka, Y.; Watanabe, S.; Le Roux, J.; Hershey, J.R., "A Generalized Discriminative Training Framework for System Combination", IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), DOI: 10.1109/ASRU.2013.6707703, December 2013, pp. 43-48.
    BibTeX Download PDFRead TR2013-118
    • @inproceedings{Tachioka2013dec,
    • author = {Tachioka, Y. and Watanabe, S. and {Le Roux}, J. and Hershey, J.R.},
    • title = {A Generalized Discriminative Training Framework for System Combination},
    • booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)},
    • year = 2013,
    • pages = {43--48},
    • month = dec,
    • doi = {10.1109/ASRU.2013.6707703},
    • url = {http://www.merl.com/publications/TR2013-118}
    • }
  •  Potluru, V.K.; Le Roux, J.; Pearlmutter, B.A.; Hershey, J.R.; Brand, M.E., "Coordinate Descent for Mixed-norm NMF", NIPS Workshop: Greedy Algorithms, Frank-Wolfe and Friends - A Modern Perspective, December 2013.
    BibTeX Download PDFRead TR2013-130
    • @inproceedings{Potluru2013dec,
    • author = {Potluru, V.K. and {Le Roux}, J. and Pearlmutter, B.A. and Hershey, J.R. and Brand, M.E.},
    • title = {Coordinate Descent for Mixed-norm NMF},
    • booktitle = {NIPS Workshop: Greedy Algorithms, Frank-Wolfe and Friends - A Modern Perspective},
    • year = 2013,
    • month = dec,
    • url = {http://www.merl.com/publications/TR2013-130}
    • }
  •  Le Roux, J.; Watanabe, S.; Hershey, J.R., "Ensemble Learning for Speech Enhancement", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), DOI: 10.1109/WASPAA.2013.6701888, ISSN: 1931-1168, October 2013, pp. 1-4.
    BibTeX Download PDFRead TR2013-098
    • @inproceedings{LeRoux2013oct,
    • author = {{Le Roux}, J. and Watanabe, S. and Hershey, J.R.},
    • title = {Ensemble Learning for Speech Enhancement},
    • booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
    • year = 2013,
    • pages = {1--4},
    • month = oct,
    • doi = {10.1109/WASPAA.2013.6701888},
    • issn = {1931-1168},
    • url = {http://www.merl.com/publications/TR2013-098}
    • }