- Isik, Y., Le Roux, J., Chen, Z., Watanabe, S., Hershey, J.R., "Single-Channel Multi-Speaker Separation using Deep Clustering", Interspeech, DOI: 10.21437/Interspeech.2016-1176, September 2016, pp. 545-549.
BibTeX TR2016-073 PDF- @inproceedings{Isik2016sep,
- author = {Isik, Yusuf and Le Roux, Jonathan and Chen, Zhuo and Watanabe, Shinji and Hershey, John R.},
- title = {Single-Channel Multi-Speaker Separation using Deep Clustering},
- booktitle = {Interspeech},
- year = 2016,
- pages = {545--549},
- month = sep,
- doi = {10.21437/Interspeech.2016-1176},
- url = {https://www.merl.com/publications/TR2016-073}
- }
- Hayashi, T., Watanabe, S., Toda, T., Hori, T., Le Roux, J., Takeda, K., "Bidirectional LSTM-HMM Hybrid System for Polyphonic Sound Event Detection", Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE), September 2016, pp. 35-39.
BibTeX TR2016-114 PDF- @inproceedings{Hayashi2016sep,
- author = {Hayashi, Tomoki and Watanabe, Shinji and Toda, Tomoki and Hori, Takaaki and Le Roux, Jonathan and Takeda, Kazuya},
- title = {Bidirectional LSTM-HMM Hybrid System for Polyphonic Sound Event Detection},
- booktitle = {Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)},
- year = 2016,
- pages = {35--39},
- month = sep,
- url = {https://www.merl.com/publications/TR2016-114}
- }
- Hershey, J.R., Chen, Z., Le Roux, J., Watanabe, S., "Deep Clustering: Discriminative Embeddings for Segmentation and Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2016.7471631, March 2016, pp. 31-35.
BibTeX TR2016-003 PDF- @inproceedings{Hershey2016mar,
- author = {Hershey, John R. and Chen, Zhuo and Le Roux, Jonathan and Watanabe, Shinji},
- title = {Deep Clustering: Discriminative Embeddings for Segmentation and Separation},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2016,
- pages = {31--35},
- month = mar,
- doi = {10.1109/ICASSP.2016.7471631},
- url = {https://www.merl.com/publications/TR2016-003}
- }
- Wisdom, S., Hershey, J.R., Le Roux, J., Watanabe, S., "Deep Unfolding for Multichannel Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2016.7471649, March 2016, pp. 121-125.
BibTeX TR2016-008 PDF- @inproceedings{Wisdom2016mar,
- author = {Wisdom, Scott and Hershey, John R. and Le Roux, Jonathan and Watanabe, Shinji},
- title = {Deep Unfolding for Multichannel Source Separation},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2016,
- pages = {121--125},
- month = mar,
- doi = {10.1109/ICASSP.2016.7471649},
- url = {https://www.merl.com/publications/TR2016-008}
- }
- Hori, T., Chen, Z., Erdogan, H., Hershey, J.R., Le Roux, J., Mitra, V., Watanabe, S., "The MERL/SRI System for the 3rd CHiME Challenge Using Beamforming, Robust Feature Extraction, and Advanced Speech Recognition", IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), DOI: 10.1109/ASRU.2015.7404833, December 2015, pp. 475-481.
BibTeX TR2015-135 PDF- @inproceedings{Hori2015dec2,
- author = {Hori, T. and Chen, Z. and Erdogan, H. and Hershey, J.R. and {Le Roux}, J. and Mitra, V. and Watanabe, S.},
- title = {The MERL/SRI System for the 3rd CHiME Challenge Using Beamforming, Robust Feature Extraction, and Advanced Speech Recognition},
- booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)},
- year = 2015,
- pages = {475--481},
- month = dec,
- publisher = {IEEE},
- doi = {10.1109/ASRU.2015.7404833},
- url = {https://www.merl.com/publications/TR2015-135}
- }
- Harsham, B.A., Watanabe, S., Esenther, A., Hershey, J.R., Le Roux, J., Luan, Y., Nikovski, D.N., Potluru, V.K., "Driver Prediction to Improve Interaction with In-Vehicle HMI", Workshop on DSP for In-Vehicle Systems and Safety (DSP), October 2015.
BibTeX TR2015-120 PDF- @inproceedings{Harsham2015oct,
- author = {Harsham, B.A. and Watanabe, S. and Esenther, A. and Hershey, J.R. and {Le Roux}, J. and Luan, Y. and Nikovski, D.N. and Potluru, V.K.},
- title = {Driver Prediction to Improve Interaction with In-Vehicle HMI},
- booktitle = {Workshop on DSP for In-Vehicle Systems and Safety (DSP)},
- year = 2015,
- month = oct,
- url = {https://www.merl.com/publications/TR2015-120}
- }
- 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, August 2015, vol. 9237, pp. 91-99.
BibTeX TR2015-094 PDF- @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 = {https://www.merl.com/publications/TR2015-094}
- }
- 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 TR2015-031 PDF- @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 = {https://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 TR2015-029 PDF- @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 = {https://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 TR2015-030 PDF- @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 = {https://www.merl.com/publications/TR2015-030}
- }
- 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}
- }
- 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}
- }