- 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}
- }
- Wang, P., Boufounos, P.T., Mansour, H., Orlik, P.V., "Slow-Time MIMO-FMCW Automotive Radar Detection with Imperfect Waveform Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP40776.2020.9053892, April 2020, pp. 8634-8638.
BibTeX TR2020-039 PDF Video- @inproceedings{Wang2020apr,
- author = {Wang, Pu and Boufounos, Petros T. and Mansour, Hassan and Orlik, Philip V.},
- title = {Slow-Time MIMO-FMCW Automotive Radar Detection with Imperfect Waveform Separation},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2020,
- pages = {8634--8638},
- month = apr,
- publisher = {IEEE},
- doi = {10.1109/ICASSP40776.2020.9053892},
- issn = {2379-190X},
- isbn = {978-1-5090-6631-5},
- url = {https://www.merl.com/publications/TR2020-039}
- }
- Li, R., Wang, X., Mallidi, H., Watanabe, S., Hori, T., Hermansky, H., "Multi-Stream End-to-End Speech Recognition", IEEE/ACM Transactions on Audio, Speech and Language Processing, DOI: 10.1109/TASLP.2019.2959721, Vol. 28, pp. 646-655, March 2020.
BibTeX TR2020-030 PDF- @article{Li2020mar,
- author = {Li, Ruizhi and Wang, Xiaofei and Mallidi, Harish and Watanabe, Shinji and Hori, Takaaki and Hermansky, Hynek},
- title = {Multi-Stream End-to-End Speech Recognition},
- journal = {IEEE/ACM Transactions on Audio, Speech and Language Processing},
- year = 2020,
- volume = 28,
- pages = {646--655},
- month = mar,
- doi = {10.1109/TASLP.2019.2959721},
- url = {https://www.merl.com/publications/TR2020-030}
- }
- 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}
- }
- Wang, P., Li, H., "Target Detection with Imperfect Waveform Separation in Distributed MIMO Radar", IEEE Transactions on Signal Processing, DOI: 10.1109/TSP.2020.2964227, Vol. 68, No. 1, pp. 793-807, January 2020.
BibTeX TR2020-007 PDF- @article{Wang2020jan,
- author = {Wang, Pu and Li, Hongbin},
- title = {Target Detection with Imperfect Waveform Separation in Distributed MIMO Radar},
- journal = {IEEE Transactions on Signal Processing},
- year = 2020,
- volume = 68,
- number = 1,
- pages = {793--807},
- month = jan,
- doi = {10.1109/TSP.2020.2964227},
- issn = {1053-587X},
- url = {https://www.merl.com/publications/TR2020-007}
- }
- 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}
- }
- Wollenstein, S., Sun, C., Zhang, J., Paschalidis, I., "Joint Estimation of OD Demands and Cost Functions in Transportation Networks from Data", IEEE Conference on Decision and Control (CDC), DOI: 10.1109/CDC40024.2019.9029445, December 2019, pp. 5113-5118.
BibTeX TR2019-144 PDF- @inproceedings{Wollenstein2019dec,
- author = {Wollenstein, Salomón and Sun, Chuangchuang and Zhang, Jing and Paschalidis, Ioannis},
- title = {Joint Estimation of OD Demands and Cost Functions in Transportation Networks from Data},
- booktitle = {IEEE Conference on Decision and Control (CDC)},
- year = 2019,
- pages = {5113--5118},
- month = dec,
- doi = {10.1109/CDC40024.2019.9029445},
- url = {https://www.merl.com/publications/TR2019-144}
- }
- Jespersen, M.H., Pajovic, M., Koike-Akino, T., Wang, Y., Popovski, P., Orlik, P.V., "Deep Learning for Synchronization and Channel Estimation in NB-IoT Random Access Channel", IEEE Global Communications Conference (GLOBECOM), DOI: 10.1109/GLOBECOM38437.2019.9013510, December 2019.
BibTeX TR2019-140 PDF- @inproceedings{Jespersen2019dec,
- author = {Jespersen, Mads Helge and Pajovic, Milutin and Koike-Akino, Toshiaki and Wang, Ye and Popovski, Petar and Orlik, Philip V.},
- title = {Deep Learning for Synchronization and Channel Estimation in NB-IoT Random Access Channel},
- booktitle = {IEEE Global Communications Conference (GLOBECOM)},
- year = 2019,
- month = dec,
- publisher = {IEEE},
- doi = {10.1109/GLOBECOM38437.2019.9013510},
- issn = {2576-6813},
- isbn = {978-1-7281-0962-6},
- url = {https://www.merl.com/publications/TR2019-140}
- }
- 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}
- }
- Karafiat, M., Baskar, M.K., Watanabe, S., Hori, T., Wiesner, M., Cernocky, J.H., "Analysis of Multilingual Sequence-to-Sequence Speech Recognition Systems", Interspeech, DOI: 10.21437/Interspeech.2019-2355//, September 2019, pp. 2019-2355.
BibTeX TR2019-103 PDF- @inproceedings{Karafiat2019sep,
- author = {Karafiat, Martin and Baskar, Murali Karthick and Watanabe, Shinji and Hori, Takaaki and Wiesner, Matthew and Cernocky, Jan, Honza},
- title = {Analysis of Multilingual Sequence-to-Sequence Speech Recognition Systems},
- booktitle = {Interspeech},
- year = 2019,
- pages = {2019--2355},
- month = sep,
- doi = {10.21437/Interspeech.2019-2355//},
- url = {https://www.merl.com/publications/TR2019-103}
- }
- 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}
- }
- Wang, J., Cherian, A., "Discriminative Video Representation Learning Using Support Vector Classifiers", IEEE Transactions on Pattern Analysis and Machine Intelligence, DOI: 10.1109/TPAMI.2019.2937292, August 2019.
BibTeX TR2019-107 PDF- @article{Wang2019aug,
- author = {Wang, Jue and Cherian, Anoop},
- title = {Discriminative Video Representation Learning Using Support Vector Classifiers},
- journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
- year = 2019,
- month = aug,
- doi = {10.1109/TPAMI.2019.2937292},
- url = {https://www.merl.com/publications/TR2019-107}
- }
- 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}
- }
- 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}
- }
- Seetharaman, P., Wichern, G., Le Roux, J., Pardo, B., "Bootstrapping Single-Channel Source Separation via Unsupervised Spatial Clustering on Stereo Mixtures", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2019.8683198, May 2019.
BibTeX TR2019-014 PDF- @inproceedings{Seetharaman2019may2,
- author = {Seetharaman, Prem and Wichern, Gordon and Le Roux, Jonathan and Pardo, Bryan},
- title = {Bootstrapping Single-Channel Source Separation via Unsupervised Spatial Clustering on Stereo Mixtures},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2019,
- month = may,
- doi = {10.1109/ICASSP.2019.8683198},
- url = {https://www.merl.com/publications/TR2019-014}
- }
- Seetharaman, P., Wichern, G., Venkataramani, S., Le Roux, J., "Class-Conditional Embeddings for Music Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2019.8683007, May 2019.
BibTeX TR2019-004 PDF- @inproceedings{Seetharaman2019may,
- author = {Seetharaman, Prem and Wichern, Gordon and Venkataramani, Shrikant and Le Roux, Jonathan},
- title = {Class-Conditional Embeddings for Music Source Separation},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2019,
- month = may,
- doi = {10.1109/ICASSP.2019.8683007},
- url = {https://www.merl.com/publications/TR2019-004}
- }
- Wang, X., Li, R., Mallidi, S.H., Hori, T., Watanabe, S., Hermansky, H., "Stream Attention-Based Multi-Array End-to-End Speech Recognition", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/ICASSP.2019.8682650, May 2019.
BibTeX TR2019-005 PDF- @inproceedings{Wang2019may,
- author = {Wang, Xiaofei and Li, Ruizhi and Mallidi, Sri Harish and Hori, Takaaki and Watanabe, Shinji and Hermansky, Hynek},
- title = {Stream Attention-Based Multi-Array End-to-End Speech Recognition},
- booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
- year = 2019,
- month = may,
- doi = {10.1109/ICASSP.2019.8682650},
- url = {https://www.merl.com/publications/TR2019-005}
- }
- Bergman, D., Cardonha, C., Cire, A., Raghunathan, A.U., "On the Minimum Chordal Completion Polytope", Operations Research, DOI: 10.1287/opre.2018.1783, Vol. 67, No. 2, pp. 295-597, March 2019.
BibTeX TR2018-095 PDF- @article{Bergman2019mar,
- author = {Bergman, David and Cardonha, Carlos and Cire, Andre and Raghunathan, Arvind},
- title = {On the Minimum Chordal Completion Polytope},
- journal = {Operations Research},
- year = 2019,
- volume = 67,
- number = 2,
- pages = {295--597},
- month = mar,
- doi = {10.1287/opre.2018.1783},
- url = {https://www.merl.com/publications/TR2018-095}
- }
- Le Roux, J., Wichern, G., Watanabe, S., Sarroff, A., Hershey, J., "Phasebook and Friends: Leveraging discrete representations for source separation", IEEE Journal of Selected Topics in Signal Processing, DOI: 10.1109/JSTSP.2019.2904183, Vol. 13, No. 2, pp. 370-382, March 2019.
BibTeX TR2018-199 PDF- @article{LeRoux2019mar,
- author = {Le Roux, Jonathan and Wichern, Gordon and Watanabe, Shinji and Sarroff, Andy and Hershey, John},
- title = {Phasebook and Friends: Leveraging discrete representations for source separation},
- journal = {IEEE Journal of Selected Topics in Signal Processing},
- year = 2019,
- volume = 13,
- number = 2,
- pages = {370--382},
- month = mar,
- doi = {10.1109/JSTSP.2019.2904183},
- url = {https://www.merl.com/publications/TR2018-199}
- }
- Pajovic, M., Ozcan, G., Koike-Akino, T., Wang, P., Orlik, P.V., "Packet Separation in Phase Noise Impaired Random Access Channel", IEEE Global Communications Conference (GLOBECOM), DOI: 10.1109/GLOCOM.2018.8647403, December 2018.
BibTeX TR2018-167 PDF- @inproceedings{Pajovic2018dec,
- author = {Pajovic, Milutin and Ozcan, Gozde and Koike-Akino, Toshiaki and Wang, Pu and Orlik, Philip V.},
- title = {Packet Separation in Phase Noise Impaired Random Access Channel},
- booktitle = {IEEE Global Communications Conference (GLOBECOM)},
- year = 2018,
- month = dec,
- doi = {10.1109/GLOCOM.2018.8647403},
- url = {https://www.merl.com/publications/TR2018-167}
- }
- Yu, X., Chaturvedi, S., Feng, C., Taguchi, Y., Lee, T.-Y., Fernandes, C., Ramalingam, S., "VLASE: Vehicle Localization by Aggregating Semantic Edges", IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), DOI: 10.1109/IROS.2018.8594358, October 2018, pp. 3196-3203.
BibTeX TR2018-113 PDF- @inproceedings{Yu2018oct,
- author = {Yu, Xin and Chaturvedi, Sagar and Feng, Chen and Taguchi, Yuichi and Lee, Teng-Yok and Fernandes, Clinton and Ramalingam, Srikumar},
- title = {VLASE: Vehicle Localization by Aggregating Semantic Edges},
- booktitle = {IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
- year = 2018,
- pages = {3196--3203},
- month = oct,
- doi = {10.1109/IROS.2018.8594358},
- url = {https://www.merl.com/publications/TR2018-113}
- }
- Wichern, G., Le Roux, J., "Phase Reconstruction with Learned Time-Frequency Representations for Single-Channel Speech Separation", International Workshop on Acoustic Signal Enhancement (IWAENC), DOI: 10.1109/IWAENC.2018.8521243, September 2018.
BibTeX TR2018-146 PDF- @inproceedings{Wichern2018sep,
- author = {Wichern, Gordon and Le Roux, Jonathan},
- title = {Phase Reconstruction with Learned Time-Frequency Representations for Single-Channel Speech Separation},
- booktitle = {International Workshop on Acoustic Signal Enhancement (IWAENC)},
- year = 2018,
- month = sep,
- doi = {10.1109/IWAENC.2018.8521243},
- url = {https://www.merl.com/publications/TR2018-146}
- }