- 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 TR2015-032 PDF- @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 = {https://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 TR2015-033 PDF- @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 = {https://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 TR2015-023 PDF- @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 = {https://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, Vol. 32, No. 2, pp. 55-66, March 2015.
BibTeX TR2014-122 PDF- @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 = {https://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 TR2014-104 PDF- @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 = {https://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, 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}
- }
- Watanabe, S., Hershey, J.R., Marks, T.K., Fujii, Y., Koji, Y., "Cost-level integration of statistical and rule-based dialog managers", Interspeech, September 2014, vol. 15, pp. 323-327.
BibTeX TR2014-082 PDF- @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},
- url = {https://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, 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}
- }
- Tuzel, O., Liu, M.-Y., Taguchi, Y., Raghunathan, A.U., "Learning to Rank 3D Features", European Conference on Computer Vision (ECCV), DOI: 10.1007/978-3-319-10590-1_34, September 2014, vol. 8689, pp. 520-535.
BibTeX TR2014-078 PDF- @inproceedings{Tuzel2014sep,
- author = {Tuzel, O. and Liu, M.-Y. and Taguchi, Y. and Raghunathan, A.U.},
- title = {{Learning to Rank 3D Features}},
- booktitle = {European Conference on Computer Vision (ECCV)},
- journal = {European Conference on Computer Vision (ECCV)},
- year = 2014,
- volume = 8689,
- series = {Lecture Notes in Computer Science},
- pages = {520--535},
- month = sep,
- doi = {10.1007/978-3-319-10590-1_34},
- issn = {0302-9743},
- isbn = {978-3-319-10589-5},
- url = {https://www.merl.com/publications/TR2014-078}
- }
- 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/1409.2574}
- }
- Jones, M., Nikovski, D., Imamura, M., Hirata, T., "Anomaly Detection in Real-valued Multidimensional Time Series", ASE Bigdata/Socialcom/Cyber Security Conference, June 2014.
BibTeX TR2014-042 PDF Software- @inproceedings{Jones2014jun,
- author = {Jones, M. and Nikovski, D. and Imamura, M. and Hirata, T.},
- title = {{Anomaly Detection in Real-valued Multidimensional Time Series}},
- booktitle = {ASE Bigdata/Socialcom/Cyber Security Conference},
- year = 2014,
- month = jun,
- publisher = {Academy of Science and Engineering (ASE)},
- isbn = {978-1-62561-000-3},
- url = {https://www.merl.com/publications/TR2014-042}
- }
- 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}
- }
- 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}
- }