Publications

59 / 3,602 publications found.


  •  Delcroix, M., Watanabe, S., "Recent Advances in Distant Speech Recognition," Tech. Rep. TR2016-115, Interspeech Tutorials, September 2016.
    BibTeX TR2016-115 PDF
    • @techreport{Delcroix2016sep,
    • author = {Delcroix, Marc and Watanabe, Shinji},
    • title = {Recent Advances in Distant Speech Recognition},
    • booktitle = {Interspeech Tutorials},
    • institution = {Interspeech},
    • year = 2016,
    • month = sep,
    • url = {https://www.merl.com/publications/TR2016-115}
    • }
  •  Le Roux, J., Vincent, E., Erdogan, H., "Learning-Based Approaches to Speech Enhancement and Separation," Tech. Rep. TR2016-113, Interspeech Tutorials, September 2016.
    BibTeX TR2016-113 PDF
    • @techreport{LeRoux2016sep,
    • author = {Le Roux, Jonathan and Vincent, Emmanuel and Erdogan, Hakan},
    • title = {Learning-Based Approaches to Speech Enhancement and Separation},
    • booktitle = {Interspeech Tutorials},
    • year = 2016,
    • month = sep,
    • url = {https://www.merl.com/publications/TR2016-113}
    • }
  •  Erdogan, H., Hershey, J.R., Watanabe, S., Mandel, M., Le Roux, J., "Improved MVDR beamforming using single-channel mask prediction networks", Interspeech, DOI: 10.21437/​Interspeech.2016-552, September 2016, pp. 1981-1985.
    BibTeX TR2016-072 PDF
    • @inproceedings{Erdogan2016sep,
    • author = {Erdogan, Hakan and Hershey, John R. and Watanabe, Shinji and Mandel, Michael and Le Roux, Jonathan},
    • title = {Improved MVDR beamforming using single-channel mask prediction networks},
    • booktitle = {Interspeech},
    • year = 2016,
    • pages = {1981--1985},
    • month = sep,
    • doi = {10.21437/Interspeech.2016-552},
    • url = {https://www.merl.com/publications/TR2016-072}
    • }
  •  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}
    • }
  •  Kamilov, U., "Parallel Proximal Methods for Total Variation Minimization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2016.74772568, March 2016, pp. 4697-4701.
    BibTeX TR2016-007 PDF
    • @inproceedings{Kamilov2016mar1,
    • author = {Kamilov, Ulugbek},
    • title = {Parallel Proximal Methods for Total Variation Minimization},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2016,
    • pages = {4697--4701},
    • month = mar,
    • doi = {10.1109/ICASSP.2016.74772568},
    • url = {https://www.merl.com/publications/TR2016-007}
    • }
  •  Xiao, X., Watanabe, S., Erdogan, H., Lu, L., Hershey, J., Seltzer, M., Chen, G., Zhang, Y., Mandel, M., Yu, D., "Deep Beamforming Networks for Multi-Channel Speech Recognition", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2016.7472778, March 2016, pp. 5745-5749.
    BibTeX TR2016-002 PDF
    • @inproceedings{Xiao2016mar,
    • author = {Xiao, Xiong and Watanabe, Shinji and Erdogan, Hakan and Lu, Liang and Hershey, John and Seltzer, Mike and Chen, Guoguo and Zhang, Yu and Mandel, Michael and Yu, Dong},
    • title = {Deep Beamforming Networks for Multi-Channel Speech Recognition},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2016,
    • pages = {5745--5749},
    • month = mar,
    • doi = {10.1109/ICASSP.2016.7472778},
    • url = {https://www.merl.com/publications/TR2016-002}
    • }
  •  Barker, J., Marxer, R., Vincent, E., Watanabe, S., "The Third 'CHiME' Speech Separation and Recognition Challenge: Dataset, Task and Baselines", IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), DOI: 10.1109/​ASRU.2015.75404837, December 2015, pp. 504-511.
    BibTeX TR2015-136 PDF
    • @inproceedings{Barker2015dec,
    • author = {Barker, J. and Marxer, R. and Vincent, E. and Watanabe, S.},
    • title = {The Third 'CHiME' Speech Separation and Recognition Challenge: Dataset, Task and Baselines},
    • booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)},
    • year = 2015,
    • pages = {504--511},
    • month = dec,
    • publisher = {IEEE},
    • doi = {10.1109/ASRU.2015.75404837},
    • url = {https://www.merl.com/publications/TR2015-136}
    • }
  •  Hsiao, R., Ma, J., Hartmann, W., Karafiat, M., Grezl, F., Burget, L., Szoke, I., Cernocky, J., Watanabe, S., Chen, Z., Mallidi, S.H., Hermansky, H., Tsakalidis, S., Schwartz, R., "Robust Speech Recognition in Unknown Reverberant and Noisy Conditions", IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), DOI: 10.1109/​ARSU.2015.7404841, December 2015, pp. 533-538.
    BibTeX TR2015-138 PDF
    • @inproceedings{Hsiao2015dec,
    • author = {Hsiao, R. and Ma, J. and Hartmann, W. and Karafiat, M. and Grezl, F. and Burget, L. and Szoke, I. and Cernocky, J. and Watanabe, S. and Chen, Z. and Mallidi, S.H. and Hermansky, H. and Tsakalidis, S. and Schwartz, R.},
    • title = {Robust Speech Recognition in Unknown Reverberant and Noisy Conditions},
    • booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)},
    • year = 2015,
    • pages = {533--538},
    • month = dec,
    • publisher = {IEEE},
    • doi = {10.1109/ARSU.2015.7404841},
    • url = {https://www.merl.com/publications/TR2015-138}
    • }
  •  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}
    • }
  •  Abdelaziz, A.H., Watanabe, S., Hershey, J.R., Vincent, E., Kolossa, D., "Uncertainty Propagation Through Deep Neural Networks", Interspeech, September 2015, vol. 1 or 5, pp. 3561.
    BibTeX TR2015-098 PDF
    • @inproceedings{Abdelaziz2015sep,
    • author = {Abdelaziz, A.H. and Watanabe, S. and Hershey, J.R. and Vincent, E. and Kolossa, D.},
    • title = {Uncertainty Propagation Through Deep Neural Networks},
    • booktitle = {Interspeech},
    • year = 2015,
    • volume = {1 or 5},
    • pages = 3561,
    • month = sep,
    • isbn = {978-1-5108-1790-6},
    • url = {https://www.merl.com/publications/TR2015-098}
    • }
  •  Chen, Z., Watanabe, S., Erdogan, H., Hershey, J.R., "Speech Enhancement and Recognition Using Multi-Task Learning of Long Short-Term Memory Recurrent Neural Networks", Interspeech, September 2015, vol. 1 of 5, pp. 1278.
    BibTeX TR2015-100 PDF
    • @inproceedings{Chen2015sep,
    • author = {Chen, Z. and Watanabe, S. and Erdogan, H. and Hershey, J.R.},
    • title = {Speech Enhancement and Recognition Using Multi-Task Learning of Long Short-Term Memory Recurrent Neural Networks},
    • booktitle = {Interspeech},
    • year = 2015,
    • volume = {1 of 5},
    • pages = 1278,
    • month = sep,
    • isbn = {978-1-5108-1790-6},
    • url = {https://www.merl.com/publications/TR2015-100}
    • }
  •  Tachioka, Y., Watanabe, S., "Uncertainty Training and Decoding Methods of Deep Neural Networks Based on Stochastic Representation of Enhanced Features", Interspeech, September 2015, vol. 1 or 5, pp. 3541.
    BibTeX TR2015-099 PDF
    • @inproceedings{Tachioka2015sep,
    • author = {Tachioka, Y. and Watanabe, S.},
    • title = {Uncertainty Training and Decoding Methods of Deep Neural Networks Based on Stochastic Representation of Enhanced Features},
    • booktitle = {Interspeech},
    • year = 2015,
    • volume = {1 or 5},
    • pages = 3541,
    • month = sep,
    • isbn = {978-1-5108-1790-6},
    • url = {https://www.merl.com/publications/TR2015-099}
    • }
  •  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}
    • }
  •  Tachioka, Y., Narita, T., Watanabe, S., "Effectiveness of Dereverberation, Feature Transformation, Discriminative Training Methods, and System Combination Approach for Various Reverberant Environments", EURASIP Journal on Advances in Signal Processing, DOI: 10.1186/​s13634-015-0241-y, June 2015.
    BibTeX TR2015-152 PDF
    • @article{Tachioka2015jun,
    • author = {Tachioka, Y. and Narita, T. and Watanabe, S.},
    • title = {Effectiveness of Dereverberation, Feature Transformation, Discriminative Training Methods, and System Combination Approach for Various Reverberant Environments},
    • journal = {EURASIP Journal on Advances in Signal Processing},
    • year = 2015,
    • month = jun,
    • doi = {10.1186/s13634-015-0241-y},
    • url = {https://www.merl.com/publications/TR2015-152}
    • }
  •  Kadambi, A., Boufounos, P.T., "Coded Aperture Compressive 3-D LIDAR", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2015.7178153, April 2015, pp. 1166-1170.
    BibTeX TR2015-028 PDF
    • @inproceedings{Kadambi2015apr,
    • author = {Kadambi, A. and Boufounos, P.T.},
    • title = {Coded Aperture Compressive 3-D LIDAR},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2015,
    • pages = {1166--1170},
    • month = apr,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP.2015.7178153},
    • url = {https://www.merl.com/publications/TR2015-028}
    • }
  •  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}
    • }
  •  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., 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}
    • }
  •  Wang, Y., Ortega, A., Tian, D., Vetro, A., "A Graph-based Joint Bilateral Approach for Depth Enhancement", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2014.6853724, May 2014, pp. 885-889.
    BibTeX TR2014-028 PDF
    • @inproceedings{Wang2014may,
    • author = {Wang, Y. and Ortega, A. and Tian, D. and Vetro, A.},
    • title = {A Graph-based Joint Bilateral Approach for Depth Enhancement},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2014,
    • pages = {885--889},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP.2014.6853724},
    • url = {https://www.merl.com/publications/TR2014-028}
    • }
  •  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}
    • }
  •  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}
    • }
  •  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}
    • }