Publications

327 / 3,736 publications found.


  •  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}
    • }
  •  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 TR2014-032 PDF
    • @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 = {https://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 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}
    • }
  •  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 TR2014-024 PDF
    • @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 = {https://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 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}
    • }
  •  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 TR2014-023 PDF
    • @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 = {https://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 TR2014-022 PDF
    • @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 = {https://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, Vol. 74, No. 3, pp. 341-358, March 2014.
    BibTeX TR2013-071 PDF
    • @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 = {https://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 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}
    • }
  •  Portelo, J., Raj, B., Boufounos, P., Trancoso, I., Abad, A., "Speaker Verification Using Secure Binary Embeddings", European Signal Processing Conference (EUSIPCO), September 2013.
    BibTeX TR2013-082 PDF
    • @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 = {https://www.merl.com/publications/TR2013-082}
    • }
  •  Tachioka, Y., Watanabe, S., "Discriminative Training of Acoustic Models for System Combination", Interspeech, August 2013.
    BibTeX TR2013-074 PDF
    • @inproceedings{Tachioka2013aug,
    • author = {Tachioka, Y. and Watanabe, S.},
    • title = {Discriminative Training of Acoustic Models for System Combination},
    • booktitle = {Interspeech},
    • year = 2013,
    • month = aug,
    • url = {https://www.merl.com/publications/TR2013-074}
    • }
  •  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}
    • }
  •  Tachioka, Y., Watanabe, S., Hershey, J.R., "Effectiveness of Discriminative Training and Feature Transformation for Reverberated and Noisy Speech", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2013.
    BibTeX TR2013-020 PDF
    • @inproceedings{Tachioka2013may,
    • author = {Tachioka, Y. and Watanabe, S. and Hershey, J.R.},
    • title = {Effectiveness of Discriminative Training and Feature Transformation for Reverberated and Noisy Speech},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2013,
    • month = may,
    • url = {https://www.merl.com/publications/TR2013-020}
    • }
  •  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}
    • }
  •  Watanabe, S., Hershey, J.R., "Stereo-based Feature Enhancement Using Dictionary Learning", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2013.6639034, May 2013, pp. 7073-7077.
    BibTeX TR2013-019 PDF
    • @inproceedings{Watanabe2013may,
    • author = {Watanabe, S. and Hershey, J.R.},
    • title = {Stereo-based Feature Enhancement Using Dictionary Learning},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2013,
    • pages = {7073--7077},
    • month = may,
    • doi = {10.1109/ICASSP.2013.6639034},
    • issn = {1520-6149},
    • url = {https://www.merl.com/publications/TR2013-019}
    • }
  •  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}
    • }
  •  Watanabe, S., Nakamura, A., "Bayesian Approaches to Acoustic Modeling: A Review", APSIPA Transactions on Signal and Information Processing, DOI: 10.1017/​ATSIP.2012.6, Vol. 1, December 2012.
    BibTeX TR2012-087 PDF
    • @article{Watanabe2012dec,
    • author = {Watanabe, S. and Nakamura, A.},
    • title = {Bayesian Approaches to Acoustic Modeling: A Review},
    • journal = {APSIPA Transactions on Signal and Information Processing},
    • year = 2012,
    • volume = 1,
    • month = dec,
    • doi = {10.1017/ATSIP.2012.6},
    • url = {https://www.merl.com/publications/TR2012-087}
    • }
  •  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}
    • }