Publications

359 / 3,666 publications found.


  •  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}
    • }
  •  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}
    • }
  •  Heaukulani, C., Le Roux, J., Hershey, J.R., "Latent Dirichlet Reallocation for Term Swapping", International Workshop on Statistical Machine Learning for Speech Processing (IWSML), March 2012.
    BibTeX TR2012-022 PDF
    • @inproceedings{Heaukulani2012mar,
    • author = {Heaukulani, C. and {Le Roux}, J. and Hershey, J.R.},
    • title = {Latent Dirichlet Reallocation for Term Swapping},
    • booktitle = {International Workshop on Statistical Machine Learning for Speech Processing (IWSML)},
    • year = 2012,
    • month = mar,
    • url = {https://www.merl.com/publications/TR2012-022}
    • }
  •  Boufounos, P.T., "Depth Sensing Using Active Coherent Illumination", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2012.6289146, March 2012, pp. 5417-5420.
    BibTeX TR2012-020 PDF Video
    • @inproceedings{Boufounos2012mar,
    • author = {Boufounos, P.T.},
    • title = {Depth Sensing Using Active Coherent Illumination},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2012,
    • pages = {5417--5420},
    • month = mar,
    • doi = {10.1109/ICASSP.2012.6289146},
    • issn = {1520-6149},
    • isbn = {978-1+4673-0045-2},
    • url = {https://www.merl.com/publications/TR2012-020}
    • }
  •  Le Roux, J., Hershey, J.R., "Indirect Model-based Speech Enhancement", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP-2012.6288806, March 2012, pp. 4045-4048.
    BibTeX TR2012-016 PDF
    • @inproceedings{LeRoux2012mar2,
    • author = {{Le Roux}, J. and Hershey, J.R.},
    • title = {Indirect Model-based Speech Enhancement},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2012,
    • pages = {4045--4048},
    • month = mar,
    • doi = {10.1109/ICASSP-2012.6288806},
    • issn = {1520-6149},
    • isbn = {978-1-4673-0045-2},
    • url = {https://www.merl.com/publications/TR2012-016}
    • }
  •  Liu, D., Boufounos, P.T., "Dictionary Learning Based Pan-Sharpening", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP.2012.6288398, March 2012, pp. 2397-2400.
    BibTeX TR2012-013 PDF
    • @inproceedings{Liu2012mar,
    • author = {Liu, D. and Boufounos, P.T.},
    • title = {Dictionary Learning Based Pan-Sharpening},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2012,
    • pages = {2397--2400},
    • month = mar,
    • doi = {10.1109/ICASSP.2012.6288398},
    • issn = {1520-6149},
    • isbn = {978-1-4673-0045-2},
    • url = {https://www.merl.com/publications/TR2012-013}
    • }