Publications

74 / 3,739 publications found.


  •  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}
    • }
  •  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}
    • }
  •  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}
    • }
  •  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}
    • }
  •  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}
    • }
  •  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., 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}
    • }
  •  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}
    • }
  •  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}
    • }
  •  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., 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}
    • }
  •  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}
    • }
  •  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}
    • }
  •  Gales, M., Watanabe, S., Fosler-Lussier, E., "Structured Discriminative Models For Speech Recognition", IEEE Signal Processing Magazine, Vol. 29, No. 6, pp. 70-81, November 2012.
    BibTeX TR2012-072 PDF
    • @article{Gales2012nov,
    • author = {Gales, M. and Watanabe, S. and Fosler-Lussier, E.},
    • title = {Structured Discriminative Models For Speech Recognition},
    • journal = {IEEE Signal Processing Magazine},
    • year = 2012,
    • volume = 29,
    • number = 6,
    • pages = {70--81},
    • month = nov,
    • url = {https://www.merl.com/publications/TR2012-072}
    • }
  •  Gouvea, E., Ezzat, T., Raj, B., "Subword Unit Approaches for Retrieval by Voice", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2010.
    BibTeX TR2010-012 PDF
    • @inproceedings{Gouvea2010mar,
    • author = {Gouvea, E. and Ezzat, T. and Raj, B.},
    • title = {Subword Unit Approaches for Retrieval by Voice},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2010,
    • month = mar,
    • url = {https://www.merl.com/publications/TR2010-012}
    • }
  •  Guinness, J., Raj, B., Schmidt-Nielsen, B., Turicchia, L., Sarpeshkar, R., "A Companding Front End for Noise-Robust Automatic Speech Recognition", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2005, vol. 1, pp. 249-252.
    BibTeX TR2005-023 PDF
    • @inproceedings{Guinness2005mar,
    • author = {Guinness, J. and Raj, B. and Schmidt-Nielsen, B. and Turicchia, L. and Sarpeshkar, R.},
    • title = {A Companding Front End for Noise-Robust Automatic Speech Recognition},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2005,
    • volume = 1,
    • pages = {249--252},
    • month = mar,
    • issn = {1520-6149},
    • url = {https://www.merl.com/publications/TR2005-023}
    • }