- Kavalerov, I., Wisdom, S., Erdogan, H., Patton, B., Wilson, K., Le Roux, J., Hershey, J., "Universal Sound Separation", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), DOI: 10.1109/WASPAA.2019.8937253, October 2019, pp. 170-174.
BibTeX TR2019-123 PDF- @inproceedings{Kavalerov2019oct,
- author = {Kavalerov, Ilya and Wisdom, Scott and Erdogan, Hakan and Patton, Brian and Wilson, Kevin and Le Roux, Jonathan and Hershey, John},
- title = {Universal Sound Separation},
- booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
- year = 2019,
- pages = {170--174},
- month = oct,
- doi = {10.1109/WASPAA.2019.8937253},
- issn = {1947-1629},
- isbn = {978-1-7281-1123-0},
- url = {https://www.merl.com/publications/TR2019-123}
- }
- Le Roux, J., Wisdom, S., Erdogan, H., Hershey, J., "SDR -- Half-Baked or Well Done?", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2019.8683855, May 2019.
BibTeX TR2019-013 PDF- @inproceedings{LeRoux2019may,
- author = {Le Roux, Jonathan and Wisdom, Scott and Erdogan, Hakan and Hershey, John},
- title = {SDR -- Half-Baked or Well Done?},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2019,
- month = may,
- doi = {10.1109/ICASSP.2019.8683855},
- url = {https://www.merl.com/publications/TR2019-013}
- }
- Erdogan, H., Hershey, J., Watanabe, S., Le Roux, J., "Deep recurrent networks for separation and recognition of single-channel speech in non-stationary background audio" in New Era for Robust Speech Recognition: Exploiting Deep Learning, Watanabe, S. and Delcroix, M. and Metze, F. and Hershey, J.R., Eds., chapter 7, Springer, July 2018.
BibTeX - @incollection{Erdogan2018jul,
- author = {Erdogan, Hakan and Hershey, John and Watanabe, Shinji and Le Roux, Jonathan},
- title = {Deep recurrent networks for separation and recognition of single-channel speech in non-stationary background audio},
- booktitle = {New Era for Robust Speech Recognition: Exploiting Deep Learning},
- year = 2018,
- editor = {Watanabe, S. and Delcroix, M. and Metze, F. and Hershey, J.R.},
- chapter = 7,
- month = jul,
- publisher = {Springer},
- isbn = {978-3-319-64680-0}
- }
- Xiao, X., Watanabe, S., Erdogan, H., Mandel, M., Lu, L., Hershey, J., Seltzer, M., Chen, G., Zhang, Y., Yu, D., "Discriminative beamforming with phase aware neural networks for speech enhancement and recognition" in New Era for Robust Speech Recognition: Exploiting Deep Learning, Watanabe, S. and Delcroix, M. and Metze, F. and Hershey, J.R., Eds., chapter 4, Springer, July 9, 2018.
BibTeX - @incollection{Xiao2018jul2,
- author = {Xiao, Xiong and Watanabe, Shinji and Erdogan, Hakan and Mandel, Michael and Lu, Liang and Hershey, John and Seltzer, Mike and Chen, Guoguo and Zhang, Yu and Yu, Dong},
- title = {Discriminative beamforming with phase aware neural networks for speech enhancement and recognition},
- booktitle = {New Era for Robust Speech Recognition: Exploiting Deep Learning},
- year = 2018,
- editor = {Watanabe, S. and Delcroix, M. and Metze, F. and Hershey, J.R.},
- chapter = 4,
- month = jul,
- publisher = {Springer}
- }
- Meng, Z., Watanabe, S., Hershey, J.R., Erdogan, H., "Deep Long Short-Term Memory Adaptive Beamforming Networks for Multichannel Robust Speech Recognition", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), March 2017.
BibTeX TR2017-012 PDF- @inproceedings{Meng2017mar,
- author = {Meng, Zhong and Watanabe, Shinji and Hershey, John R. and Erdogan, Hakan},
- title = {Deep Long Short-Term Memory Adaptive Beamforming Networks for Multichannel Robust Speech Recognition},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2017,
- month = mar,
- url = {https://www.merl.com/publications/TR2017-012}
- }
- 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}
- }
- 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}
- }
- 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}
- }
- 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}
- }
- 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}
- }
- Erdogan, H., Hershey, J.R., Watanabe, S., Le Roux, J., "Phase-Sensitive and Recognition-Boosted Speech Separation Using Deep Recurrent Neural Networks", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2015.7178061, April 2015, pp. 708-712.
BibTeX TR2015-031 PDF- @inproceedings{Erdogan2015apr,
- author = {Erdogan, H. and Hershey, J.R. and Watanabe, S. and {Le Roux}, J.},
- title = {Phase-Sensitive and Recognition-Boosted Speech Separation Using Deep Recurrent Neural Networks},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2015,
- pages = {708--712},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP.2015.7178061},
- url = {https://www.merl.com/publications/TR2015-031}
- }
- Topkaya, I.S., Erdogan, H., Porikli, F., "Detecting and Tracking Unknown Number of Objects with Dirichlet Process Mixture Models and Markov Random Fields", International Symposium on Visual Computing (ISVC), July 2013.
BibTeX TR2013-078 PDF- @inproceedings{Topkaya2013jul,
- author = {Topkaya, I.S. and Erdogan, H. and Porikli, F.},
- title = {Detecting and Tracking Unknown Number of Objects with Dirichlet Process Mixture Models and Markov Random Fields},
- booktitle = {International Symposium on Visual Computing (ISVC)},
- year = 2013,
- month = jul,
- url = {https://www.merl.com/publications/TR2013-078}
- }