Publications

390 / 3,947 publications found.


  •  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}
    • }
  •  Zhang, J., Chen, L., Boufounos, P.T., Gu, Y., "On the Theoretical Analysis of Cross Validation in Compressive Sensing", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2014.6854225, May 2014, pp. 3370-3374.
    BibTeX TR2014-025 PDF
    • @inproceedings{Zhang2014may,
    • author = {Zhang, J. and Chen, L. and Boufounos, P.T. and Gu, Y.},
    • title = {{On the Theoretical Analysis of Cross Validation in Compressive Sensing}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2014,
    • pages = {3370--3374},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP.2014.6854225},
    • url = {https://www.merl.com/publications/TR2014-025}
    • }
  •  Mansour, H., Vetro, A., "Video Background Subtraction Using Semi-supervised Robust Matrix Completion", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2014.6854862, May 2014, pp. 6528-6532.
    BibTeX TR2014-026 PDF
    • @inproceedings{Mansour2014may,
    • author = {Mansour, H. and Vetro, A.},
    • title = {{Video Background Subtraction Using Semi-supervised Robust Matrix Completion}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2014,
    • pages = {6528--6532},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP.2014.6854862},
    • url = {https://www.merl.com/publications/TR2014-026}
    • }
  •  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}
    • }
  •  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}
    • }
  •  Tawara, N., Ogawa, T., Watanabe, S., Nakamura, A., Kobayashi, T., "Blocked Gibbs Sampling Based Multi-Scale Mixture Model for Speaker Clustering on Noisy Data", IEEE International Workshop on Machine Learning for Signal Processing (MLSP), DOI: 10.1109/​MLSP.2013.6661902, September 2013, pp. 1-6.
    BibTeX TR2013-091 PDF
    • @inproceedings{Tawara2013sep,
    • author = {Tawara, N. and Ogawa, T. and Watanabe, S. and Nakamura, A. and Kobayashi, T.},
    • title = {{Blocked Gibbs Sampling Based Multi-Scale Mixture Model for Speaker Clustering on Noisy Data}},
    • booktitle = {IEEE International Workshop on Machine Learning for Signal Processing (MLSP)},
    • year = 2013,
    • pages = {1--6},
    • month = sep,
    • doi = {10.1109/MLSP.2013.6661902},
    • issn = {1551-2541},
    • url = {https://www.merl.com/publications/TR2013-091}
    • }
  •  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}
    • }
  •  Garg, R., Rane, S., "A Keypoint Descriptor for Alignment-Free Fingerprint Matching", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2013.
    BibTeX TR2013-023 PDF
    • @inproceedings{Garg2013may,
    • author = {Garg, R. and Rane, S.},
    • title = {{A Keypoint Descriptor for Alignment-Free Fingerprint Matching}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2013,
    • month = may,
    • url = {https://www.merl.com/publications/TR2013-023}
    • }
  •  Hu, S., Cohen, R.A., Vetro, A., Kuo, C.C.J., "Screen Content Coding for HEVC Using Edge Modes", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2013.
    BibTeX TR2013-034 PDF
    • @inproceedings{Hu2013may,
    • author = {Hu, S. and Cohen, R.A. and Vetro, A. and Kuo, C.C.J.},
    • title = {{Screen Content Coding for HEVC Using Edge Modes}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2013,
    • month = may,
    • url = {https://www.merl.com/publications/TR2013-034}
    • }
  •  Le Roux, J., Boufounos, P.T., Kang, K., Hershey, J.R., "Source Localization in Reverberant Environments using Sparse Optimization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2013.6638473, May 2013, pp. 4310-4314.
    BibTeX TR2013-022 PDF
    • @inproceedings{LeRoux2013may,
    • author = {{Le Roux}, J. and Boufounos, P.T. and Kang, K. and Hershey, J.R.},
    • title = {{Source Localization in Reverberant Environments using Sparse Optimization}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2013,
    • pages = {4310--4314},
    • month = may,
    • doi = {10.1109/ICASSP.2013.6638473},
    • issn = {1520-6149},
    • url = {https://www.merl.com/publications/TR2013-022}
    • }
  •  Liu, D., Boufounos, P.T., "Random Steerable Arrays for Synthetic Aperture Imaging", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2013.6638371, May 2013, pp. 3811-3815.
    BibTeX TR2013-035 PDF Video
    • @inproceedings{Liu2013may,
    • author = {Liu, D. and Boufounos, P.T.},
    • title = {{Random Steerable Arrays for Synthetic Aperture Imaging}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2013,
    • pages = {3811--3815},
    • month = may,
    • doi = {10.1109/ICASSP.2013.6638371},
    • issn = {1520-6149},
    • url = {https://www.merl.com/publications/TR2013-035}
    • }
  •  Rzeszutek, R., Tian, D., Vetro, A., "Disparity Estimation of Misaligned Images in a Scanline Optimization Framework", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2013.
    BibTeX TR2013-025 PDF
    • @inproceedings{Rzeszutek2013may,
    • author = {Rzeszutek, R. and Tian, D. and Vetro, A.},
    • title = {{Disparity Estimation of Misaligned Images in a Scanline Optimization Framework}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2013,
    • month = may,
    • url = {https://www.merl.com/publications/TR2013-025}
    • }
  •  Song, J.X., Sahinoglu, Z., Guo, J., "Transient Disturbance Detection for Power Systems with a General Likelihood Ratio Test", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), May 2013.
    BibTeX TR2013-024 PDF
    • @inproceedings{Song2013may,
    • author = {Song, J.X. and Sahinoglu, Z. and Guo, J.},
    • title = {{Transient Disturbance Detection for Power Systems with a General Likelihood Ratio Test}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2013,
    • month = may,
    • url = {https://www.merl.com/publications/TR2013-024}
    • }
  •  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}
    • }
  •  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}
    • }
  •  Pathak, M.A., Raj, B., Rane, S., Samaragdis, P., "Privacy-preserving Speech Processing: Cryptographic and String-Matching Frameworks Show Promise", IEEE Signal Processing Magazine, March 2013.
    BibTeX TR2013-063 PDF
    • @article{Pathak2013feb,
    • author = {Pathak, M.A. and Raj, B. and Rane, S. and Samaragdis, P.},
    • title = {{Privacy-preserving Speech Processing: Cryptographic and String-Matching Frameworks Show Promise}},
    • journal = {IEEE Signal Processing Magazine},
    • year = 2013,
    • month = feb,
    • url = {https://www.merl.com/publications/TR2013-063}
    • }
  •  Watanabe, S., Nakamura, A., "Bayesian Approaches to Acoustic Modeling: A Review", APSIPA Transactions on Signal and Information Processing, DOI: 10.1017/​ATSIP.2012.6, Vol. 1, December 2012.
    BibTeX TR2012-087 PDF
    • @article{Watanabe2012dec,
    • author = {Watanabe, S. and Nakamura, A.},
    • title = {{Bayesian Approaches to Acoustic Modeling: A Review}},
    • journal = {APSIPA Transactions on Signal and Information Processing},
    • year = 2012,
    • volume = 1,
    • month = dec,
    • doi = {10.1017/ATSIP.2012.6},
    • url = {https://www.merl.com/publications/TR2012-087}
    • }