Publications

193 / 2,449 publications found.


  •  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}
    • }
  •  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}
    • }
  •  Watanabe, S.; Le Roux, J., "Black Box Optimization for Automatic Speech Recognition", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2014.6854202, May 2014, pp. 3256-3260.
    BibTeX Download PDFRead TR2014-021
    • @inproceedings{Watanabe2014may,
    • author = {Watanabe, S. and {Le Roux}, J.},
    • title = {Black Box Optimization for Automatic Speech Recognition},
    • booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
    • year = 2014,
    • pages = {3256--3260},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP.2014.6854202},
    • url = {http://www.merl.com/publications/TR2014-021}
    • }
  •  Weng, C.; Yu, D.; Watanabe, S.; Juang, B.-H.F., "Recurrent Deep Neural Networks for Robust Speech Recognition", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2014.6854661, May 2014, pp. 5532-5536.
    BibTeX Download PDFRead TR2014-023
    • @inproceedings{Weng2014may,
    • author = {Weng, C. and Yu, D. and Watanabe, S. and Juang, B.-H.F.},
    • title = {Recurrent Deep Neural Networks for Robust Speech Recognition},
    • booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
    • year = 2014,
    • pages = {5532--5536},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP.2014.6854661},
    • url = {http://www.merl.com/publications/TR2014-023}
    • }
  •  Weninger, F.; Watanabe, S.; Tachioka, Y.; Schuller, B., "Deep Recurrent De-noising Auto-encoder and Blind De-reverberation for Reverberated Speech Recognition", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2014.6854478, May 2014, pp. 4623-4627.
    BibTeX Download PDFRead TR2014-022
    • @inproceedings{Weninger2014may1,
    • author = {Weninger, F. and Watanabe, S. and Tachioka, Y. and Schuller, B.},
    • title = {Deep Recurrent De-noising Auto-encoder and Blind De-reverberation for Reverberated Speech Recognition},
    • booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
    • year = 2014,
    • pages = {4623--4627},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP.2014.6854478},
    • url = {http://www.merl.com/publications/TR2014-022}
    • }
  •  Watanabe, S.; Nakamura, A.; Juang, B.-H., "Structural Bayesian Linear Regression for Hidden Markov Models", Journal of Signal Processing Systems, DOI: 10.1007/s11265-013-0785-8, ISSN: 1939-8018, Vol. 74, No. 3, pp. 341-358, March 2014.
    BibTeX Download PDFRead TR2013-071
    • @article{Watanabe2013aug,
    • author = {Watanabe, S. and Nakamura, A. and Juang, B.-H.},
    • title = {Structural Bayesian Linear Regression for Hidden Markov Models},
    • journal = {Journal of Signal Processing Systems},
    • year = 2014,
    • volume = 74,
    • number = 3,
    • pages = {341--358},
    • month = mar,
    • doi = {10.1007/s11265-013-0785-8},
    • issn = {1939-8018},
    • url = {http://www.merl.com/publications/TR2013-071}
    • }
  •  Vincent, E.; Barker, J.; Watanabe, S.; Le Roux, J.; Nesta, F.; Matassoni, M., "The Second CHiME Speech Separation and Recognition Challenge: An Overview of Challenge Systems and Outcomes", IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), DOI: 10.1109/ASRU.2013.6707723, December 2013, pp. 162-167.
    BibTeX Download PDFRead TR2013-119
    • @inproceedings{Vincent2013dec,
    • author = {Vincent, E. and Barker, J. and Watanabe, S. and {Le Roux}, J. and Nesta, F. and Matassoni, M.},
    • title = {The Second CHiME Speech Separation and Recognition Challenge: An Overview of Challenge Systems and Outcomes},
    • booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)},
    • year = 2013,
    • pages = {162--167},
    • month = dec,
    • doi = {10.1109/ASRU.2013.6707723},
    • url = {http://www.merl.com/publications/TR2013-119}
    • }
  •  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}
    • }
  •  Portelo, J.; Raj, B.; Boufounos, P.; Trancoso, I.; Abad, A., "Speaker Verification Using Secure Binary Embeddings", European Signal Processing Conference (EUSIPCO), September 2013.
    BibTeX Download PDFRead TR2013-082
    • @inproceedings{Portelo2013sep,
    • author = {Portelo, J. and Raj, B. and Boufounos, P. and Trancoso, I. and Abad, A.},
    • title = {Speaker Verification Using Secure Binary Embeddings},
    • booktitle = {European Signal Processing Conference (EUSIPCO)},
    • year = 2013,
    • month = sep,
    • url = {http://www.merl.com/publications/TR2013-082}
    • }