Publications

202 / 2,513 publications found.


  •  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}
    • }
  •  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}
    • }
  •  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 Download PDFRead TR2015-032
    • @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 = {http://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 Download PDFRead TR2015-033
    • @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 = {http://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 Download PDFRead TR2015-023
    • @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 = {http://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, ISSN: 1053-5888, Vol. 32, No. 2, pp. 55-66, March 2015.
    BibTeX Download PDFRead TR2014-122
    • @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 = {http://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 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}
    • }
  •  Le Roux, J.; Vincent, E., "A Categorization of Robust Speech Processing Datasets," Tech. Rep. TR2014-116, Mitsubishi Electric Research Laboratories, September 2014.
    BibTeX Download PDFRead TR2014-116
    • @techreport{LeRouxVincent2014TRdatasets,
    • author = {{Le Roux}, J. and Vincent, E.},
    • title = {A Categorization of Robust Speech Processing Datasets},
    • institution = {MERL - Mitsubishi Electric Research Laboratories},
    • year = 2014,
    • number = {TR2014-116},
    • address = {Cambridge MA, USA},
    • month = sep,
    • note = {v2014-09},
    • url = {http://www.merl.com/publications/TR2014-116}
    • }
  •  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}
    • }
  •  Tachioka, Y.; Narita, T.; Watanabe, S.; Le Roux, J., "Ensemble Integration of Calibrated Speaker Localization and Statistical Speech Detection in Domestic Environments", Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), DOI: 10.1109/HSCMA.2014.6843272, May 2014, pp. 162-166.
    BibTeX Download PDFRead TR2014-034
    • @inproceedings{Tachioka2014may2,
    • author = {Tachioka, Y. and Narita, T. and Watanabe, S. and {Le Roux}, J.},
    • title = {Ensemble Integration of Calibrated Speaker Localization and Statistical Speech Detection in Domestic Environments},
    • booktitle = {Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA)},
    • year = 2014,
    • pages = {162--166},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/HSCMA.2014.6843272},
    • url = {http://www.merl.com/publications/TR2014-034}
    • }
  •  Tachioka, Y.; Narita, T.; Weninger, F.; Watanabe, S., "Dual system combination approach for various reverberant environments with dereverberation techniques", IEEE REVERB Workshop, May 2014.
    BibTeX Download PDFRead TR2014-032
    • @inproceedings{Tachioka2014may,
    • author = {Tachioka, Y. and Narita, T. and Weninger, F. and Watanabe, S.},
    • title = {Dual system combination approach for various reverberant environments with dereverberation techniques},
    • booktitle = {IEEE REVERB Workshop},
    • year = 2014,
    • month = may,
    • url = {http://www.merl.com/publications/TR2014-032}
    • }
  •  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}
    • }