Publications

149 / 3,612 publications found.


  •  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}
    • }
  •  Weninger, F., Le Roux, J., Hershey, J.R., Watanabe, S., "Discriminative NMF and its application to single-channel source separation", Interspeech, September 2014, vol. 15, pp. 865-869.
    BibTeX TR2014-081 PDF
    • @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 = {https://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 TR2014-116 PDF
    • @techreport{LeRouxVincent2014TRdatasets,
    • author = {{Le Roux}, J. and Vincent, E.},
    • title = {A Categorization of Robust Speech Processing Datasets},
    • institution = {Mitsubishi Electric Research Laboratories},
    • year = 2014,
    • number = {TR2014-116},
    • address = {Cambridge MA, USA},
    • month = sep,
    • note = {v2014-09},
    • url = {https://www.merl.com/publications/TR2014-116}
    • }
  •  Hershey, J.R., Le Roux, J., Weninger, F., "Deep Unfolding: Model-Based Inspiration of Novel Deep Architectures", arXiv, August 2014.
    BibTeX arXiv
    • @article{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 = {https://arxiv.org/abs/1409.2574v1}
    • }
  •  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 TR2014-034 PDF
    • @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 = {https://www.merl.com/publications/TR2014-034}
    • }
  •  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 TR2014-033 PDF
    • @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 = {https://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 TR2014-027 PDF Software
    • @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 = {https://www.merl.com/publications/TR2014-027}
    • }
  •  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 TR2014-021 PDF
    • @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 = {https://www.merl.com/publications/TR2014-021}
    • }
  •  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 TR2013-118 PDF
    • @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 = {https://www.merl.com/publications/TR2013-118}
    • }
  •  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 TR2013-119 PDF
    • @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 = {https://www.merl.com/publications/TR2013-119}
    • }
  •  Potluru, V.K., Le Roux, J., Pearlmutter, B.A., Hershey, J.R., Brand, M., "Coordinate Descent for Mixed-norm NMF", NIPS Workshop on Greedy Algorithms, Frank-Wolfe and Friends - A Modern Perspective, December 2013.
    BibTeX TR2013-130 PDF
    • @inproceedings{Potluru2013dec,
    • author = {Potluru, V.K. and {Le Roux}, J. and Pearlmutter, B.A. and Hershey, J.R. and Brand, M.},
    • title = {Coordinate Descent for Mixed-norm NMF},
    • booktitle = {NIPS Workshop on Greedy Algorithms, Frank-Wolfe and Friends - A Modern Perspective},
    • year = 2013,
    • month = dec,
    • url = {https://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, October 2013, pp. 1-4.
    BibTeX TR2013-098 PDF
    • @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 = {https://www.merl.com/publications/TR2013-098}
    • }
  •  Simsekli, U., Le Roux, J., Hershey, J.R., "Hierarchical and Coupled Non-negative Dynamical Systems with Application to Audio Modeling", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), DOI: 10.1109/​WASPAA.2013.6701891, October 2013, pp. 1-4.
    BibTeX TR2013-097 PDF
    • @inproceedings{Simsekli2013oct,
    • author = {Simsekli, U. and {Le Roux}, J. and Hershey, J.R.},
    • title = {Hierarchical and Coupled Non-negative Dynamical Systems with Application to Audio Modeling},
    • booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
    • year = 2013,
    • pages = {1--4},
    • month = oct,
    • doi = {10.1109/WASPAA.2013.6701891},
    • issn = {1931-1168},
    • url = {https://www.merl.com/publications/TR2013-097}
    • }
  •  Yoshino, K., Watanabe, S., Le Roux, J., Hershey, J.R., "Statistical Dialogue Management using Intention Dependency Graph", International Joint Conference on Natural Language Processing (IJCNLP), October 2013.
    BibTeX TR2013-096 PDF
    • @inproceedings{Yoshino2013oct,
    • author = {Yoshino, K. and Watanabe, S. and {Le Roux}, J. and Hershey, J.R.},
    • title = {Statistical Dialogue Management using Intention Dependency Graph},
    • booktitle = {International Joint Conference on Natural Language Processing (IJCNLP)},
    • year = 2013,
    • month = oct,
    • url = {https://www.merl.com/publications/TR2013-096}
    • }
  •  Tachioka, Y., Watanabe, S., Le Roux, J., Hershey, J.R., "Discriminative Methods for Noise Robust Speech Recognition: A CHiME Challenge Benchmark", International Workshop on Machine Listening in Multisource Environments (CHiME), June 2013.
    BibTeX TR2013-044 PDF
    • @inproceedings{Tachioka2013jun,
    • author = {Tachioka, Y. and Watanabe, S. and {Le Roux}, J. and Hershey, J.R.},
    • title = {Discriminative Methods for Noise Robust Speech Recognition: A CHiME Challenge Benchmark},
    • booktitle = {International Workshop on Machine Listening in Multisource Environments (CHiME)},
    • year = 2013,
    • month = jun,
    • url = {https://www.merl.com/publications/TR2013-044}
    • }
  •  Fevotte, C., Le Roux, J., Hershey, J.R., "Non-negative Dynamical System with Application to Speech and Audio", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2013.
    BibTeX TR2013-021 PDF Software
    • @inproceedings{Fevotte2013may,
    • author = {Fevotte, C. and {Le Roux}, J. and Hershey, J.R.},
    • title = {Non-negative Dynamical System with Application to Speech and Audio},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2013,
    • month = may,
    • url = {https://www.merl.com/publications/TR2013-021}
    • }
  •  Le Roux, J., Boufounos, P.T., Kang, K., Hershey, J.R., "Source Localization in Reverberant Environments using Sparse Optimization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2013.6638473, May 2013, pp. 4310-4314.
    BibTeX TR2013-022 PDF
    • @inproceedings{LeRoux2013may,
    • author = {{Le Roux}, J. and Boufounos, P.T. and Kang, K. and Hershey, J.R.},
    • title = {Source Localization in Reverberant Environments using Sparse Optimization},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2013,
    • pages = {4310--4314},
    • month = may,
    • doi = {10.1109/ICASSP.2013.6638473},
    • issn = {1520-6149},
    • url = {https://www.merl.com/publications/TR2013-022}
    • }
  •  Vincent, E., Barker, J., Watanabe, S., Le Roux, J., Nesta, F., Matassoni, M., "The Second 'CHiME' Speech Separation and Recognition Challenge: Datasets, Tasks and Baselines", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2013.
    BibTeX TR2013-079 PDF
    • @inproceedings{Vincent2013may,
    • 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: Datasets, Tasks and Baselines},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2013,
    • month = may,
    • url = {https://www.merl.com/publications/TR2013-079}
    • }
  •  Potluru, V.K., Plis, S.M., Le Roux, J., Pearlmutter, B.A., Calhoun, V.D., Hayes, T.P., "Block Coordinate Descent for Sparse NMF", International Conference on Learning Representations (ICLR), May 2013.
    BibTeX TR2013-026 PDF
    • @inproceedings{Potluru2013may,
    • author = {Potluru, V.K. and Plis, S.M. and {Le Roux}, J. and Pearlmutter, B.A. and Calhoun, V.D. and Hayes, T.P.},
    • title = {Block Coordinate Descent for Sparse NMF},
    • booktitle = {International Conference on Learning Representations (ICLR)},
    • year = 2013,
    • month = may,
    • url = {https://www.merl.com/publications/TR2013-026}
    • }
  •  Le Roux, J., Vincent, E., "Consistent Wiener Filtering for Audio Source Separation", IEEE Signal Processing Letters, DOI: 10.1109/​LSP.2012.2225617, Vol. 20, No. 3, pp. 217-220, March 2013.
    BibTeX TR2012-090 PDF
    • @article{LeRoux2013mar,
    • author = {{Le Roux}, J. and Vincent, E.},
    • title = {Consistent Wiener Filtering for Audio Source Separation},
    • journal = {IEEE Signal Processing Letters},
    • year = 2013,
    • volume = 20,
    • number = 3,
    • pages = {217--220},
    • month = mar,
    • doi = {10.1109/LSP.2012.2225617},
    • url = {https://www.merl.com/publications/TR2012-090}
    • }
  •  Hershey, J.R., Rennie, S.J., Le Roux, J., "Factorial Models for Noise Robust Speech Recognition" in Techniques for Noise Robustness in Automatic Speech Recognition, Virtanen, T. and Singh, R. and Raj, B., Eds., chapter 12, Wiley, November 2012.
    BibTeX TR2012-002 PDF
    • @incollection{Hershey2012nov,
    • author = {Hershey, J.R. and Rennie, S.J. and {Le Roux}, J.},
    • title = {Factorial Models for Noise Robust Speech Recognition},
    • booktitle = {Techniques for Noise Robustness in Automatic Speech Recognition},
    • year = 2012,
    • editor = {Virtanen, T. and Singh, R. and Raj, B.},
    • chapter = 12,
    • month = nov,
    • publisher = {Wiley},
    • url = {https://www.merl.com/publications/TR2012-002}
    • }
  •  Heaukulani, C., Le Roux, J., Hershey, J.R., "Latent Dirichlet Reallocation for Term Swapping", International Workshop on Statistical Machine Learning for Speech Processing (IWSML), March 2012.
    BibTeX TR2012-022 PDF
    • @inproceedings{Heaukulani2012mar,
    • author = {Heaukulani, C. and {Le Roux}, J. and Hershey, J.R.},
    • title = {Latent Dirichlet Reallocation for Term Swapping},
    • booktitle = {International Workshop on Statistical Machine Learning for Speech Processing (IWSML)},
    • year = 2012,
    • month = mar,
    • url = {https://www.merl.com/publications/TR2012-022}
    • }
  •  Le Roux, J., Hershey, J.R., "Indirect Model-based Speech Enhancement", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP-2012.6288806, March 2012, pp. 4045-4048.
    BibTeX TR2012-016 PDF
    • @inproceedings{LeRoux2012mar2,
    • author = {{Le Roux}, J. and Hershey, J.R.},
    • title = {Indirect Model-based Speech Enhancement},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2012,
    • pages = {4045--4048},
    • month = mar,
    • doi = {10.1109/ICASSP-2012.6288806},
    • issn = {1520-6149},
    • isbn = {978-1-4673-0045-2},
    • url = {https://www.merl.com/publications/TR2012-016}
    • }
  •  Le Roux, J., Hershey, J.R., "Speech Enhancement by Indirect VTS", Acoustical Society of Japan Spring Meeting (ASJ), March 2012.
    BibTeX TR2012-011 PDF
    • @inproceedings{LeRoux2012mar1,
    • author = {{Le Roux}, J. and Hershey, J.R.},
    • title = {Speech Enhancement by Indirect VTS},
    • booktitle = {Acoustical Society of Japan Spring Meeting (ASJ)},
    • year = 2012,
    • month = mar,
    • url = {https://www.merl.com/publications/TR2012-011}
    • }