- Manilow, E., Wichern, G., Le Roux, J., "Hierarchical Musical Instrument Separation", International Society for Music Information Retrieval (ISMIR) Conference, October 2020, pp. 376-383.
BibTeX TR2020-136 PDF Software- @inproceedings{Manilow2020oct,
- author = {Manilow, Ethan and Wichern, Gordon and Le Roux, Jonathan},
- title = {Hierarchical Musical Instrument Separation},
- booktitle = {International Society for Music Information Retrieval (ISMIR) Conference},
- year = 2020,
- pages = {376--383},
- month = oct,
- isbn = {978-0-9813537-0-8},
- url = {https://www.merl.com/publications/TR2020-136}
- }
- Seetharaman, P., Wichern, G., Pardo, B., Le Roux, J., "Autoclip: Adaptive Gradient Clipping For Source Separation Networks", IEEE International Workshop on Machine Learning for Signal Processing (MLSP), DOI: 10.1109/MLSP49062.2020.9231926, September 2020.
BibTeX TR2020-132 PDF- @inproceedings{Seetharaman2020sep,
- author = {Seetharaman, Prem and Wichern, Gordon and Pardo, Bryan and Le Roux, Jonathan},
- title = {Autoclip: Adaptive Gradient Clipping For Source Separation Networks},
- booktitle = {IEEE International Workshop on Machine Learning for Signal Processing (MLSP)},
- year = 2020,
- month = sep,
- publisher = {IEEE},
- doi = {10.1109/MLSP49062.2020.9231926},
- url = {https://www.merl.com/publications/TR2020-132}
- }
- Gao, P., Hori, C., Geng, S., Hori, T., Le Roux, J., "Multi-Pass Transformer for Machine Translation", arXiv, September 2020.
BibTeX arXiv- @article{Gao2020sep,
- author = {Gao, Peng and Hori, Chiori and Geng, Shijie and Hori, Takaaki and Le Roux, Jonathan},
- title = {Multi-Pass Transformer for Machine Translation},
- journal = {arXiv},
- year = 2020,
- month = sep,
- url = {https://arxiv.org/abs/2009.11382}
- }
- Pishdadian, F., Wichern, G., Le Roux, J., "Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision", IEEE/ACM Transactions on Audio, Speech, and Language Processing, DOI: 10.1109/TASLP.2020.3013105, Vol. 28, pp. 2386-2399, September 2020.
BibTeX TR2020-126 PDF- @article{Pishdadian2020sep,
- author = {Pishdadian, Fatemeh and Wichern, Gordon and Le Roux, Jonathan},
- title = {Finding Strength in Weakness: Learning to Separate Sounds with Weak Supervision},
- journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
- year = 2020,
- volume = 28,
- pages = {2386--2399},
- month = sep,
- doi = {10.1109/TASLP.2020.3013105},
- url = {https://www.merl.com/publications/TR2020-126}
- }
- Seetharaman, P., Wichern, G., Le Roux, J., Pardo, B., "Bootstrapping Unsupervised Deep Music Separation from Primitive Auditory Grouping Principles", ICML 2020 Workshop on Self-supervision in Audio and Speech, July 2020.
BibTeX TR2020-111 PDF- @inproceedings{Seetharaman2020jul,
- author = {Seetharaman, Prem and Wichern, Gordon and Le Roux, Jonathan and Pardo, Bryan},
- title = {Bootstrapping Unsupervised Deep Music Separation from Primitive Auditory Grouping Principles},
- booktitle = {ICML 2020 Workshop on Self-supervision in Audio and Speech},
- year = 2020,
- month = jul,
- url = {https://www.merl.com/publications/TR2020-111}
- }
- Geng, S., Gao, P., Hori, C., Le Roux, J., Cherian, A., "Spatio-Temporal Scene Graphs for Video Dialog", arXiv, July 2020.
BibTeX arXiv- @article{Geng2020jul,
- author = {Geng, Shijie and Gao, Peng and Hori, Chiori and Le Roux, Jonathan and Cherian, Anoop},
- title = {Spatio-Temporal Scene Graphs for Video Dialog},
- journal = {arXiv},
- year = 2020,
- month = jul,
- url = {https://arxiv.org/abs/2007.03848}
- }
- Chang, X., Zhang, W., Qian, Y., Le Roux, J., Watanabe, S., "End-To-End Multi-Speaker Speech Recognition with Transformer", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP40776.2020.9054029, April 2020, pp. 6134-6138.
BibTeX TR2020-043 PDF Video Presentation- @inproceedings{Chang2020apr,
- author = {Chang, Xuankai and Zhang, Wangyou and Qian, Yanmin and Le Roux, Jonathan and Watanabe, Shinji},
- title = {End-To-End Multi-Speaker Speech Recognition with Transformer},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2020,
- pages = {6134--6138},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP40776.2020.9054029},
- issn = {2379-190X},
- isbn = {978-1-5090-6631-5},
- url = {https://www.merl.com/publications/TR2020-043}
- }
- Pishdadian, F., Wichern, G., Le Roux, J., "Learning to Separate Sounds From Weakly Labeled Scenes", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP40776.2020.9053055, April 2020, pp. 91-95.
BibTeX TR2020-038 PDF Video Presentation- @inproceedings{Pishdadian2020apr,
- author = {Pishdadian, Fatemeh and Wichern, Gordon and Le Roux, Jonathan},
- title = {Learning to Separate Sounds From Weakly Labeled Scenes},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2020,
- pages = {91--95},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP40776.2020.9053055},
- issn = {2379-190X},
- isbn = {978-1-5090-6631-5},
- url = {https://www.merl.com/publications/TR2020-038}
- }
- Maciejewski, M., Wichern, G., McQuinn, E., Le Roux, J., "WHAMR!: Noisy and Reverberant Single-Channel Speech Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP40776.2020.9053327, April 2020, pp. 696-700.
BibTeX TR2020-042 PDF Video Presentation- @inproceedings{Maciejewski2020apr,
- author = {Maciejewski, Matthew and Wichern, Gordon and McQuinn, Emmett and Le Roux, Jonathan},
- title = {WHAMR!: Noisy and Reverberant Single-Channel Speech Separation},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2020,
- pages = {696--700},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP40776.2020.9053327},
- issn = {2379-190X},
- isbn = {978-1-5090-6631-5},
- url = {https://www.merl.com/publications/TR2020-042}
- }
- Moritz, N., Hori, T., Le Roux, J., "Streaming Automatic Speech Recognition With The Transformer Model", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP40776.2020.9054476, April 2020, pp. 6074-6078.
BibTeX TR2020-040 PDF Video Presentation- @inproceedings{Moritz2020apr,
- author = {Moritz, Niko and Hori, Takaaki and Le Roux, Jonathan},
- title = {Streaming Automatic Speech Recognition With The Transformer Model},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2020,
- pages = {6074--6078},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP40776.2020.9054476},
- issn = {2379-190X},
- isbn = {978-1-5090-6631-5},
- url = {https://www.merl.com/publications/TR2020-040}
- }
- Sari, L., Moritz, N., Hori, T., Le Roux, J., "Unsupervised Speaker Adaptation Using Attention-Based Speaker Memory For End-To-End ASR", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP40776.2020.9054249, April 2020, pp. 7384-7388.
BibTeX TR2020-037 PDF Video Presentation- @inproceedings{Sari2020apr,
- author = {Sari, Leda and Moritz, Niko and Hori, Takaaki and Le Roux, Jonathan},
- title = {Unsupervised Speaker Adaptation Using Attention-Based Speaker Memory For End-To-End ASR},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2020,
- pages = {7384--7388},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP40776.2020.9054249},
- issn = {2379-190X},
- isbn = {978-1-5090-6631-5},
- url = {https://www.merl.com/publications/TR2020-037}
- }
- Aihara, R., Wichern, G., Le Roux, J., "Deep clusteringによる シングルチャネル音声分離とその発展", The Journal of the Acoustical Society of Japan, DOI: 10.20697/jasj.76.2_101, Vol. 76, No. 2, pp. 101-108, April 2020.
BibTeX J-STAGE- @article{Aihara2020apr,
- author = {{Aihara, Ryo and Wichern, Gordon and Le Roux, Jonathan}},
- title = {Deep clusteringによる シングルチャネル音声分離とその発展},
- journal = {The Journal of the Acoustical Society of Japan},
- year = 2020,
- volume = 76,
- number = 2,
- pages = {101--108},
- month = apr,
- doi = {10.20697/jasj.76.2_101},
- url = {https://www.jstage.jst.go.jp/article/jasj/76/2/76_101/_article/-char/en}
- }
- Aihara, R., Wichern, G., Le Roux, J., "Deep Clustering-based Single Channel Speech Separation and Recent Advances", Acoustical Science and Technology, DOI: 10.1250/ast.41.465, Vol. 41, No. 2, pp. 465-471, March 2020.
BibTeX TR2021-020 PDF- @article{Aihara2020jun,
- author = {{Aihara, Ryo and Wichern, Gordon and Le Roux, Jonathan}},
- title = {Deep Clustering-based Single Channel Speech Separation and Recent Advances},
- journal = {Acoustical Science and Technology},
- year = 2020,
- volume = 41,
- number = 2,
- pages = {465--471},
- month = mar,
- doi = {10.1250/ast.41.465},
- url = {https://www.merl.com/publications/TR2021-020}
- }
- Chang, X., Zhang, W., Qian, Y., Le Roux, J., Watanabe, S., "MIMO-Speech: End-to-End Multi-Channel Multi-Speaker Speech Recognition", IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), December 2019, pp. 237-144.
BibTeX TR2019-157 PDF- @inproceedings{Chang2019dec,
- author = {Chang, Xuankai and Zhang, Wangyou and Qian, Yanmin and Le Roux, Jonathan and Watanabe, Shinji},
- title = {MIMO-Speech: End-to-End Multi-Channel Multi-Speaker Speech Recognition},
- booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)},
- year = 2019,
- pages = {237--144},
- month = dec,
- isbn = {978-1-7281-0305-1},
- url = {https://www.merl.com/publications/TR2019-157}
- }
- Moritz, N., Hori, T., Le Roux, J., "Streaming End-to-End Speech Recognition with Joint CTC-Attention Based Models", IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), December 2019, pp. 936-943.
BibTeX TR2019-159 PDF- @inproceedings{Moritz2019dec,
- author = {Moritz, Niko and Hori, Takaaki and Le Roux, Jonathan},
- title = {Streaming End-to-End Speech Recognition with Joint CTC-Attention Based Models},
- booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)},
- year = 2019,
- pages = {936--943},
- month = dec,
- isbn = {978-1-7281-0305-1},
- url = {https://www.merl.com/publications/TR2019-159}
- }
- 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}
- }
- Manilow, E., Wichern, G., Seetharaman, P., Le Roux, J., "Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), DOI: 10.1109/WASPAA.2019.8937170, October 2019, pp. 45-49.
BibTeX TR2019-124 PDF- @inproceedings{Manilow2019oct,
- author = {Manilow, Ethan and Wichern, Gordon and Seetharaman, Prem and Le Roux, Jonathan},
- title = {Cutting Music Source Separation Some Slakh: A Dataset to Study the Impact of Training Data Quality and Quantity},
- booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
- year = 2019,
- pages = {45--49},
- month = oct,
- doi = {10.1109/WASPAA.2019.8937170},
- issn = {1947-1629},
- isbn = {978-1-7281-1123-0},
- url = {https://www.merl.com/publications/TR2019-124}
- }
- Moritz, N., Hori, T., Le Roux, J., "Unidirectional Neural Network Architectures for End-to-End Automatic Speech Recognition", Interspeech, DOI: 10.21437/Interspeech.2019-2837, September 2019, pp. 76-80.
BibTeX TR2019-098 PDF- @inproceedings{Moritz2019sep,
- author = {Moritz, Niko and Hori, Takaaki and Le Roux, Jonathan},
- title = {Unidirectional Neural Network Architectures for End-to-End Automatic Speech Recognition},
- booktitle = {Interspeech},
- year = 2019,
- pages = {76--80},
- month = sep,
- doi = {10.21437/Interspeech.2019-2837},
- url = {https://www.merl.com/publications/TR2019-098}
- }
- Seki, H., Hori, T., Watanabe, S., Le Roux, J., Hershey, J., "End-to-End Multilingual Multi-Speaker Speech Recognition", Interspeech, DOI: 10.21437/Interspeech.2019-3038, September 2019, pp. 3755-3759.
BibTeX TR2019-101 PDF- @inproceedings{Seki2019sep,
- author = {Seki, Hiroshi and Hori, Takaaki and Watanabe, Shinji and Le Roux, Jonathan and Hershey, John},
- title = {End-to-End Multilingual Multi-Speaker Speech Recognition},
- booktitle = {Interspeech},
- year = 2019,
- pages = {3755--3759},
- month = sep,
- doi = {10.21437/Interspeech.2019-3038},
- url = {https://www.merl.com/publications/TR2019-101}
- }
- Seki, H., Hori, T., Watanabe, S., Moritz, N., Le Roux, J., "Vectorized Beam Search for CTC-Attention-based Speech Recognition", Interspeech, DOI: 10.21437/Interspeech.2019-2860, September 2019, pp. 3825-3829.
BibTeX TR2019-102 PDF- @inproceedings{Seki2019sep2,
- author = {Seki, Hiroshi and Hori, Takaaki and Watanabe, Shinji and Moritz, Niko and Le Roux, Jonathan},
- title = {Vectorized Beam Search for CTC-Attention-based Speech Recognition},
- booktitle = {Interspeech},
- year = 2019,
- pages = {3825--3829},
- month = sep,
- doi = {10.21437/Interspeech.2019-2860},
- url = {https://www.merl.com/publications/TR2019-102}
- }
- Wichern, G., McQuinn, E., Antognini, J., Flynn, M., Zhu, R., Crow, D., Manilow, E., Le Roux, J., "WHAM!: Extending Speech Separation to Noisy Environments", Interspeech, DOI: 10.21437/Interspeech.2019-2821, September 2019, pp. 1368-1372.
BibTeX TR2019-099 PDF- @inproceedings{Wichern2019sep,
- author = {Wichern, Gordon and McQuinn, Emmett and Antognini, Joe and Flynn, Michael and Zhu, Richard and Crow, Dwight and Manilow, Ethan and Le Roux, Jonathan},
- title = {WHAM!: Extending Speech Separation to Noisy Environments},
- booktitle = {Interspeech},
- year = 2019,
- pages = {1368--1372},
- month = sep,
- doi = {10.21437/Interspeech.2019-2821},
- url = {https://www.merl.com/publications/TR2019-099}
- }
- Aihara, R., Hanazawa, T., Okato, Y., Wichern, G., Le Roux, J., "Teacher-Student Deep Clustering For Low-Delay Channel Speech Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2019.8682695, May 2019.
BibTeX TR2019-003 PDF- @inproceedings{Aihara2019may,
- author = {{Aihara, Ryo and Hanazawa, Toshiyuki and Okato, Yohei and Wichern, Gordon and Le Roux, Jonathan}},
- title = {Teacher-Student Deep Clustering For Low-Delay Channel Speech Separation},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2019,
- month = may,
- doi = {10.1109/ICASSP.2019.8682695},
- url = {https://www.merl.com/publications/TR2019-003}
- }
- Hori, T., Astudillo, R., Hayashi, T., Zhang, Y., Watanabe, S., Le Roux, J., "Cycle-Consistency Training for End-to-End Speech Recognition", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2019.8683307, May 2019.
BibTeX TR2019-002 PDF- @inproceedings{Hori2019may,
- author = {Hori, Takaaki and Astudillo, Ramon and Hayashi, Tomoki and Zhang, Yu and Watanabe, Shinji and Le Roux, Jonathan},
- title = {Cycle-Consistency Training for End-to-End Speech Recognition},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2019,
- month = may,
- doi = {10.1109/ICASSP.2019.8683307},
- url = {https://www.merl.com/publications/TR2019-002}
- }
- Le Roux, J., Wichern, G., Watanabe, S., Sarroff, A., Hershey, J., "The Phasebook: Building Complex Masks via Discrete Representations for Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2019.8682587, May 2019.
BibTeX TR2019-008 PDF- @inproceedings{LeRoux2019may2,
- author = {Le Roux, Jonathan and Wichern, Gordon and Watanabe, Shinji and Sarroff, Andy and Hershey, John},
- title = {The Phasebook: Building Complex Masks via Discrete Representations for Source Separation},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2019,
- month = may,
- doi = {10.1109/ICASSP.2019.8682587},
- url = {https://www.merl.com/publications/TR2019-008}
- }
- 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}
- }