- Tachioka, Y., Narita, T., Miura, I., Uramoto, T., Monta, N., Uenohara, S., Furuya, K., Watanabe, S., Le Roux, J., "Coupled initialization of multi-channel non-negative matrix factorization based on spatial and spectral information", Interspeech, August 2017.
- Hayashi, T., Watanabe, S., Toda, T., Hori, T., Le Roux, J., Takeda, K., "Duration-Controlled LSTM for Polyphonic Sound Event Detection", IEEE/ACM Transactions on Audio, Speech, and Language Processing, DOI: 10.1109/TASLP.2017.2740002, ISSN: 2329-9304, Vol. 25, No. 11, August 2017.
- Hayashi, T., Watanabe, S., Toda, T., Hori, T., Le Roux, J., Takeda, K., "BLSTM-HMM Hybrid System Combined with Sound Activity Detection Network for Polyphonic Sound Event Detection", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
- Hayashi, T., Watanabe, S., Toda, T., Hori, T., Le Roux, J., Takeda, K., "Bidirectional LSTM-HMM Hybrid System for Polyphonic Sound Event Detection", Detection and Classification of Acoustic Scenes and Events Workshop, September 2016, pp. 35-39.
- 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 Download PDFRead TR2015-029- @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 = {http://www.merl.com/publications/TR2015-029}
- }
- 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}
- }
- 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}
- }
- Mansour, H.; Rane, S.; Boufounos, P.T.; Vetro, A., "Video Querying Via Compact Descriptors of Visually Salient Objects", IEEE International Conference on Image Processing (ICIP), DOI: 10.1109/ICIP.2014.7025564, October 2014, pp. 2789-2793.
BibTeX Download PDFRead TR2014-101- @inproceedings{Mansour2014oct,
- author = {Mansour, H. and Rane, S. and Boufounos, P.T. and Vetro, A.},
- title = {Video Querying Via Compact Descriptors of Visually Salient Objects},
- booktitle = {IEEE International Conference on Image Processing (ICIP)},
- year = 2014,
- pages = {2789--2793},
- month = oct,
- doi = {10.1109/ICIP.2014.7025564},
- url = {http://www.merl.com/publications/TR2014-101}
- }
- 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}
- }
- 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}
- }
- Ni, J.; Marks, T.K.; Tuzel, O.; Porikli, F., "Detecting 3D geometric Boundaries of Indoor Scenes Under Varying Lighting", IEEE Winter Conference on Applications of Computer Vision (WACV), March 2014.
BibTeX Download PDFRead TR2014-013- @inproceedings{Ni2014mar,
- author = {Ni, J. and Marks, T.K. and Tuzel, O. and Porikli, F.},
- title = {Detecting 3D geometric Boundaries of Indoor Scenes Under Varying Lighting},
- booktitle = {IEEE Winter Conference on Applications of Computer Vision (WACV)},
- year = 2014,
- month = mar,
- url = {http://www.merl.com/publications/TR2014-013}
- }
- 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, ISSN: 1931-1168, October 2013, pp. 1-4.
BibTeX Download PDFRead TR2013-097- @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 = {http://www.merl.com/publications/TR2013-097}
- }
- 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 Download PDFRead TR2013-021- @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 = {http://www.merl.com/publications/TR2013-021}
- }
- Brand, M.; Chen, D., "Parallel Quadratic Programming for Image Processing", IEEE International Conference on Image Processing (ICIP), DOI: 10.1109/ICIP.2011.6116089, September 2011, pp. 2261-2264.
BibTeX Download PDFRead TR2011-064- @inproceedings{Brand2011sep,
- author = {Brand, M. and Chen, D.},
- title = {Parallel Quadratic Programming for Image Processing},
- booktitle = {IEEE International Conference on Image Processing (ICIP)},
- year = 2011,
- pages = {2261--2264},
- month = sep,
- doi = {10.1109/ICIP.2011.6116089},
- url = {http://www.merl.com/publications/TR2011-064}
- }
- Raj, B.; Wilson, K.W.; Krueger, A.; Haeb-Umbach, R., "Ungrounded Independent Non-Negative Factor Analysis", Annual Conference of the International Speech Communication Association, September 2010, pp. 330-333.
BibTeX Download PDFRead TR2010-122- @inproceedings{Raj2010sep,
- author = {Raj, B. and Wilson, K.W. and Krueger, A. and Haeb-Umbach, R.},
- title = {Ungrounded Independent Non-Negative Factor Analysis},
- booktitle = {Annual Conference of the International Speech Communication Association},
- year = 2010,
- pages = {330--333},
- month = sep,
- url = {http://www.merl.com/publications/TR2010-122}
- }
- Wilson, K.W.; Raj, B., "Spectrogram Dimensionality Reduction with Independence Constraints", IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), March 2010.
BibTeX Download PDFRead TR2010-023- @inproceedings{Wilson2010mar,
- author = {Wilson, K.W. and Raj, B.},
- title = {Spectrogram Dimensionality Reduction with Independence Constraints},
- booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
- year = 2010,
- month = mar,
- url = {http://www.merl.com/publications/TR2010-023}
- }
- Wilson, K. W.; Raj, B.; Smaragdis, P., "Regularized Non-negative Matrix Factorization with Temporal Dependencies for Speech Denoising", Interspeech, September 2008.
BibTeX Download PDFRead TR2008-075- @inproceedings{Wilson2008sep,
- author = {Wilson, K. W. and Raj, B. and Smaragdis, P.},
- title = {Regularized Non-negative Matrix Factorization with Temporal Dependencies for Speech Denoising},
- booktitle = {Interspeech},
- year = 2008,
- month = sep,
- url = {http://www.merl.com/publications/TR2008-075}
- }
- Madhusudana Shashanka, Bhiksha Raj, Paris Smaragdis, "Probabilistic Latent Variable Models as Non-Negative Factorizations", Tech. Rep. TR2007-083, Mitsubishi Electric Research Laboratories, Cambridge, MA, December 2007.
BibTeX Download PDFRead TR2007-083- @techreport{MERL_TR2007-083,
- author = {Madhusudana Shashanka and Bhiksha Raj and Paris Smaragdis},
- title = {Probabilistic Latent Variable Models as Non-Negative Factorizations},
- institution = {MERL - Mitsubishi Electric Research Laboratories},
- address = {Cambridge, MA 02139},
- number = {TR2007-083},
- month = dec,
- year = 2007,
- url = {http://www.merl.com/publications/TR2007-083/}
- }
- Paris Smaragdis, Bhiksha Raj, "Shift-Invariant Probabilistic Latent Component Analysis", Tech. Rep. TR2007-009, Mitsubishi Electric Research Laboratories, Cambridge, MA, December 2007.
BibTeX Download PDFRead TR2007-009- @techreport{MERL_TR2007-009,
- author = {Paris Smaragdis and Bhiksha Raj},
- title = {Shift-Invariant Probabilistic Latent Component Analysis},
- institution = {MERL - Mitsubishi Electric Research Laboratories},
- address = {Cambridge, MA 02139},
- number = {TR2007-009},
- month = dec,
- year = 2007,
- url = {http://www.merl.com/publications/TR2007-009/}
- }
- Smaragdis, P., "Convolutive Speech Bases and their Application to Supervised Speech Separation", IEEE Transactions on Audio, Speech and Language Processing, ISSN: 1558-7916, Vol. 15, No. 1, pp. 1-12, January 2007.
BibTeX Download PDFRead TR2007-002- @article{Smaragdis2007jan2,
- author = {Smaragdis, P.},
- title = {Convolutive Speech Bases and their Application to Supervised Speech Separation},
- journal = {IEEE Transactions on Audio, Speech and Language Processing},
- year = 2007,
- volume = 15,
- number = 1,
- pages = {1--12},
- month = jan,
- issn = {1558-7916},
- url = {http://www.merl.com/publications/TR2007-002}
- }