Publications

286 / 3,400 publications found.


  •  Wang, Z.-Q., Wichern, G., Watanabe, S., Le Roux, J., "STFT-Domain Neural Speech Enhancement with Very Low Algorithmic Latency", IEEE/ACM Transactions on Audio, Speech, and Language Processing, December 2022.
    BibTeX TR2022-166 PDF
    • @article{Wang2022dec2,
    • author = {Wang, Zhong-Qiu and Wichern, Gordon and Watanabe, Shinji and Le Roux, Jonathan},
    • title = {STFT-Domain Neural Speech Enhancement with Very Low Algorithmic Latency},
    • journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    • year = 2022,
    • month = dec,
    • url = {https://www.merl.com/publications/TR2022-166}
    • }
  •  Venkatesh, S., Wichern, G., Subramanian, A.S., Le Roux, J., "Improved Domain Generalization via Disentangled Multi-Task Learning in Unsupervised Anomalous Sound Detection", DCASE Workshop, Lagrange, M. and Mesaros, A. and Pellegrini, T. and Richard, G. and Serizel, R. and Stowell, D., Eds., November 2022.
    BibTeX TR2022-146 PDF Presentation
    • @inproceedings{Venkatesh2022nov,
    • author = {Venkatesh, Satvik and Wichern, Gordon and Subramanian, Aswin Shanmugam and Le Roux, Jonathan},
    • title = {Improved Domain Generalization via Disentangled Multi-Task Learning in Unsupervised Anomalous Sound Detection},
    • booktitle = {DCASE Workshop},
    • year = 2022,
    • editor = {Lagrange, M. and Mesaros, A. and Pellegrini, T. and Richard, G. and Serizel, R. and Stowell, D.},
    • month = nov,
    • isbn = {978-952-03-2677-7},
    • url = {https://www.merl.com/publications/TR2022-146}
    • }
  •  Chatterjee, M., Ahuja, N., Cherian, A., "Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation", Advances in Neural Information Processing Systems (NeurIPS), November 2022.
    BibTeX TR2022-140 PDF
    • @inproceedings{Chatterjee2022nov,
    • author = {Chatterjee, Moitreya and Ahuja, Narendra and Cherian, Anoop},
    • title = {Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation},
    • booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    • year = 2022,
    • month = nov,
    • url = {https://www.merl.com/publications/TR2022-140}
    • }
  •  Paul, S., Roy Chowdhury, A.K., Cherian, A., "AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments", Advances in Neural Information Processing Systems (NeurIPS), October 2022.
    BibTeX TR2022-131 PDF Video
    • @inproceedings{Paul2022oct2,
    • author = {Paul, Sudipta and Roy Chowdhury, Amit K and Cherian, Anoop},
    • title = {AVLEN: Audio-Visual-Language Embodied Navigation in 3D Environments},
    • booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
    • year = 2022,
    • month = oct,
    • url = {https://www.merl.com/publications/TR2022-131}
    • }
  •  Hori, C., Hori, T., Le Roux, J., "Low-Latency Streaming Scene-aware Interaction Using Audio-Visual Transformers", Interspeech, DOI: 10.21437/​Interspeech.2022-10891, September 2022, pp. 4511-4515.
    BibTeX TR2022-116 PDF
    • @inproceedings{Hori2022sep,
    • author = {Hori, Chiori and Hori, Takaaki and Le Roux, Jonathan},
    • title = {Low-Latency Streaming Scene-aware Interaction Using Audio-Visual Transformers},
    • booktitle = {Interspeech},
    • year = 2022,
    • pages = {4511--4515},
    • month = sep,
    • doi = {10.21437/Interspeech.2022-10891},
    • url = {https://www.merl.com/publications/TR2022-116}
    • }
  •  Tzinis, E., Wichern, G., Subramanian, A.S., Smaragdis, P., Le Roux, J., "Heterogeneous Target Speech Separation", Interspeech, DOI: 10.21437/​Interspeech.2022-10717, September 2022, pp. 1796-1800.
    BibTeX TR2022-115 PDF
    • @inproceedings{Tzinis2022sep,
    • author = {Tzinis, Efthymios and Wichern, Gordon and Subramanian, Aswin Shanmugam and Smaragdis, Paris and Le Roux, Jonathan},
    • title = {Heterogeneous Target Speech Separation},
    • booktitle = {Interspeech},
    • year = 2022,
    • pages = {1796--1800},
    • month = sep,
    • doi = {10.21437/Interspeech.2022-10717},
    • url = {https://www.merl.com/publications/TR2022-115}
    • }
  •  Higuchi, Y., Moritz, N., Le Roux, J., Hori, T., "Momentum Pseudo-Labeling: Semi-Supervised ASR with Continuously Improving Pseudo-Labels", IEEE Journal of Selected Topics in Signal Processing, DOI: 10.1109/​JSTSP.2022.3195367, Vol. 16, No. 6, pp. 1424-1438, September 2022.
    BibTeX TR2022-112 PDF
    • @article{Higuchi2022sep,
    • author = {Higuchi, Yosuke and Moritz, Niko and Le Roux, Jonathan and Hori, Takaaki},
    • title = {Momentum Pseudo-Labeling: Semi-Supervised ASR with Continuously Improving Pseudo-Labels},
    • journal = {IEEE Journal of Selected Topics in Signal Processing},
    • year = 2022,
    • volume = 16,
    • number = 6,
    • pages = {1424--1438},
    • month = sep,
    • doi = {10.1109/JSTSP.2022.3195367},
    • issn = {1941-0484},
    • url = {https://www.merl.com/publications/TR2022-112}
    • }
  •  Venkatesh, S., Wichern, G., Subramanian, A.S., Le Roux, J., "Disentangled Surrogate Task Learning for Improved Domain Generalization in Unsupervised Anomolous Sound Detection," Tech. Rep. TR2022-092, Detection and Classification of Acoustic Scenes and Events (DCASE) Challenge 2022, July 2022.
    BibTeX TR2022-092 PDF Presentation
    • @techreport{Venkatesh2022jul,
    • author = {Venkatesh, Satvik and Wichern, Gordon and Subramanian, Aswin Shanmugam and Le Roux, Jonathan},
    • title = {Disentangled Surrogate Task Learning for Improved Domain Generalization in Unsupervised Anomolous Sound Detection},
    • institution = {DCASE2022 Challenge},
    • year = 2022,
    • month = jul,
    • url = {https://www.merl.com/publications/TR2022-092}
    • }
  •  Chatterjee, M., Ahuja, N., Cherian, A., "Quantifying Predictive Uncertainty for Stochastic Video Synthesis from Audio", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), June 2022.
    BibTeX TR2022-082 PDF
    • @inproceedings{Chatterjee2022jun,
    • author = {Chatterjee, Moitreya and Ahuja, Narendra and Cherian, Anoop},
    • title = {Quantifying Predictive Uncertainty for Stochastic Video Synthesis from Audio},
    • booktitle = {Sight and Sound Workshop at CVPR 2022},
    • year = 2022,
    • month = jun,
    • url = {https://www.merl.com/publications/TR2022-082}
    • }
  •  Chang, X., Moritz, N., Hori, T., Watanabe, S., Le Roux, J., "Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP43922.2022.9747375, April 2022, pp. 7322-7326.
    BibTeX TR2022-021 PDF
    • @inproceedings{Chang2022apr,
    • author = {Chang, Xuankai and Moritz, Niko and Hori, Takaaki and Watanabe, Shinji and Le Roux, Jonathan},
    • title = {Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2022,
    • pages = {7322--7326},
    • month = apr,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP43922.2022.9747375},
    • url = {https://www.merl.com/publications/TR2022-021}
    • }
  •  Higuchi, Y., Moritz, N., Le Roux, J., Hori, T., "Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP43922.2022.9746275, April 2022, pp. 7672-7676.
    BibTeX TR2022-026 PDF
    • @inproceedings{Higuchi2022apr,
    • author = {Higuchi, Yosuke and Moritz, Niko and Le Roux, Jonathan and Hori, Takaaki},
    • title = {Advancing Momentum Pseudo-Labeling with Conformer and Initialization Strategy},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2022,
    • pages = {7672--7676},
    • month = apr,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP43922.2022.9746275},
    • url = {https://www.merl.com/publications/TR2022-026}
    • }
  •  Moritz, N., Hori, T., Watanabe, S., Le Roux, J., "Sequence Transduction with Graph-based Supervision", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP43922.2022.9747788, April 2022, pp. 7212-7216.
    BibTeX TR2022-024 PDF
    • @inproceedings{Moritz2022apr,
    • author = {Moritz, Niko and Hori, Takaaki and Watanabe, Shinji and Le Roux, Jonathan},
    • title = {Sequence Transduction with Graph-based Supervision},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2022,
    • pages = {7212--7216},
    • month = apr,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP43922.2022.9747788},
    • url = {https://www.merl.com/publications/TR2022-024}
    • }
  •  Petermann, D., Wichern, G., Wang, Z.-Q., Le Roux, J., "The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP43922.2022.9746005, April 2022, pp. 526-530.
    BibTeX TR2022-022 PDF Data Software
    • @inproceedings{Petermann2022apr,
    • author = {Petermann, Darius and Wichern, Gordon and Wang, Zhong-Qiu and Le Roux, Jonathan},
    • title = {The Cocktail Fork Problem: Three-Stem Audio Separation for Real-World Soundtracks},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2022,
    • pages = {526--530},
    • month = apr,
    • doi = {10.1109/ICASSP43922.2022.9746005},
    • url = {https://www.merl.com/publications/TR2022-022}
    • }
  •  Shah, A.P., Geng, S., Gao, P., Cherian, A., Hori, T., Marks, T.K., Le Roux, J., Hori, C., "Audio-Visual Scene-Aware Dialog and Reasoning Using Audio-Visual Transformers with Joint Student-Teacher Learning", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), April 2022, pp. 7732-7736.
    BibTeX TR2022-019 PDF
    • @inproceedings{Shah2022apr,
    • author = {Shah, Ankit Parag and Geng, Shijie and Gao, Peng and Cherian, Anoop and Hori, Takaaki and Marks, Tim K. and Le Roux, Jonathan and Hori, Chiori},
    • title = {Audio-Visual Scene-Aware Dialog and Reasoning Using Audio-Visual Transformers with Joint Student-Teacher Learning},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2022,
    • pages = {7732--7736},
    • month = apr,
    • publisher = {IEEE},
    • issn = {1520-6149},
    • isbn = {978-1-6654-0540-9},
    • url = {https://www.merl.com/publications/TR2022-019}
    • }
  •  Slizovskaia, O., Wichern, G., Wang, Z.-Q., Le Roux, J., "Locate This, Not That: Class-Conditioned Sound Event DOA Estimation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP43922.2022.9747604, April 2022, pp. 711-715.
    BibTeX TR2022-023 PDF
    • @inproceedings{Slizovskaia2022mar,
    • author = {Slizovskaia, Olga and Wichern, Gordon and Wang, Zhong-Qiu and Le Roux, Jonathan},
    • title = {Locate This, Not That: Class-Conditioned Sound Event DOA Estimation},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2022,
    • pages = {711--715},
    • month = apr,
    • doi = {10.1109/ICASSP43922.2022.9747604},
    • url = {https://www.merl.com/publications/TR2022-023}
    • }
  •  Hori, C., Shah, A.P., Geng, S., Gao, P., Cherian, A., Hori, T., Le Roux, J., Marks, T.K., "Overview of Audio Visual Scene-Aware Dialog with Reasoning Track for Natural Language Generation in DSTC10", The 10th Dialog System Technology Challenge Workshop at AAAI, February 2022.
    BibTeX TR2022-016 PDF
    • @inproceedings{Hori2022feb,
    • author = {Hori, Chiori and Shah, Ankit Parag and Geng, Shijie and Gao, Peng and Cherian, Anoop and Hori, Takaaki and Le Roux, Jonathan and Marks, Tim K.},
    • title = {Overview of Audio Visual Scene-Aware Dialog with Reasoning Track for Natural Language Generation in DSTC10},
    • booktitle = {The 10th Dialog System Technology Challenge Workshop at AAAI},
    • year = 2022,
    • month = feb,
    • url = {https://www.merl.com/publications/TR2022-016}
    • }
  •  Shah, A.P., Hori, T., Le Roux, J., Hori, C., DSTC10-AVSD Submission System with Reasoning using Audio-Visual Transformers with Joint Student-Teacher Learning, February 2022.
    BibTeX TR2022-025 PDF
    • @book{Shah2022feb,
    • author = {Shah, Ankit Parag and Hori, Takaaki and Le Roux, Jonathan and Hori, Chiori},
    • title = {DSTC10-AVSD Submission System with Reasoning using Audio-Visual Transformers with Joint Student-Teacher Learning},
    • year = 2022,
    • month = feb,
    • url = {https://www.merl.com/publications/TR2022-025}
    • }
  •  Cherian, A., Hori, C., Marks, T.K., Le Roux, J., "(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering", AAAI Conference on Artificial Intelligence, DOI: 10.1609/​aaai.v36i1.19922, February 2022, pp. 444-453.
    BibTeX TR2022-014 PDF Video Presentation
    • @inproceedings{Cherian2022feb,
    • author = {Cherian, Anoop and Hori, Chiori and Marks, Tim K. and Le Roux, Jonathan},
    • title = {(2.5+1)D Spatio-Temporal Scene Graphs for Video Question Answering},
    • booktitle = {Proceedings of the AAAI Conference on Artificial Intelligence},
    • year = 2022,
    • pages = {444--453},
    • month = feb,
    • doi = {10.1609/aaai.v36i1.19922},
    • url = {https://www.merl.com/publications/TR2022-014}
    • }
  •  Wang, Z.-Q., Wichern, G., Le Roux, J., "Convolutive Prediction for Monaural Speech Dereverberation and Noisy-Reverberant Speaker Separation", IEEE/ACM Transactions on Audio, Speech, and Language Processing, DOI: 10.1109/​TASLP.2021.3129363, Vol. 29, pp. 3476-3490, December 2021.
    BibTeX TR2021-144 PDF
    • @article{Wang2021dec,
    • author = {Wang, Zhong-Qiu and Wichern, Gordon and Le Roux, Jonathan},
    • title = {Convolutive Prediction for Monaural Speech Dereverberation and Noisy-Reverberant Speaker Separation},
    • journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    • year = 2021,
    • volume = 29,
    • pages = {3476--3490},
    • month = dec,
    • doi = {10.1109/TASLP.2021.3129363},
    • url = {https://www.merl.com/publications/TR2021-144}
    • }
  •  Wang, Z.-Q., Wichern, G., Le Roux, J., "On The Compensation Between Magnitude and Phase in Speech Separation", IEEE Signal Processing Letters, DOI: 10.1109/​LSP.2021.3116502, Vol. 28, pp. 2018-2022, November 2021.
    BibTeX TR2021-137 PDF
    • @article{Wang2021nov2,
    • author = {Wang, Zhong-Qiu and Wichern, Gordon and Le Roux, Jonathan},
    • title = {On The Compensation Between Magnitude and Phase in Speech Separation},
    • journal = {IEEE Signal Processing Letters},
    • year = 2021,
    • volume = 28,
    • pages = {2018--2022},
    • month = nov,
    • doi = {10.1109/LSP.2021.3116502},
    • url = {https://www.merl.com/publications/TR2021-137}
    • }
  •  Wang, Z.-Q., Wichern, G., Le Roux, J., "Convolutive Prediction for Reverberant Speech Separation", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), DOI: 10.1109/​WASPAA52581.2021.9632667, October 2021, pp. 56-60.
    BibTeX TR2021-127 PDF
    • @inproceedings{Wang2021oct4,
    • author = {Wang, Zhong-Qiu and Wichern, Gordon and Le Roux, Jonathan},
    • title = {Convolutive Prediction for Reverberant Speech Separation},
    • booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
    • year = 2021,
    • pages = {56--60},
    • month = oct,
    • publisher = {IEEE},
    • doi = {10.1109/WASPAA52581.2021.9632667},
    • url = {https://www.merl.com/publications/TR2021-127}
    • }
  •  Wichern, G., Chakrabarty, A., Wang, Z.-Q., Le Roux, J., "Anomalous sound detection using attentive neural processes", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), DOI: 10.1109/​WASPAA52581.2021.9632762, October 2021, pp. 186-190.
    BibTeX TR2021-129 PDF
    • @inproceedings{Wichern2021oct,
    • author = {Wichern, Gordon and Chakrabarty, Ankush and Wang, Zhong-Qiu and Le Roux, Jonathan},
    • title = {Anomalous sound detection using attentive neural processes},
    • booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
    • year = 2021,
    • pages = {186--190},
    • month = oct,
    • publisher = {IEEE},
    • doi = {10.1109/WASPAA52581.2021.9632762},
    • url = {https://www.merl.com/publications/TR2021-129}
    • }
  •  Chatterjee, M., Le Roux, J., Ahuja, N., Cherian, A., "Visual Scene Graphs for Audio Source Separation", IEEE International Conference on Computer Vision (ICCV), October 2021, pp. 1204-1213.
    BibTeX TR2021-095 PDF Video Software
    • @inproceedings{Chatterjee2021oct,
    • author = {Chatterjee, Moitreya and Le Roux, Jonathan and Ahuja, Narendra and Cherian, Anoop},
    • title = {Visual Scene Graphs for Audio Source Separation},
    • booktitle = {IEEE International Conference on Computer Vision (ICCV)},
    • year = 2021,
    • pages = {1204--1213},
    • month = oct,
    • publisher = {CVF},
    • url = {https://www.merl.com/publications/TR2021-095}
    • }
  •  Higuchi, Y., Moritz, N., Le Roux, J., Hori, T., "Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition", Interspeech, DOI: 10.21437/​Interspeech.2021-571, September 2021, pp. 726-730.
    BibTeX TR2021-103 PDF
    • @inproceedings{Higuchi2021sep,
    • author = {Higuchi, Yosuke and Moritz, Niko and Le Roux, Jonathan and Hori, Takaaki},
    • title = {Momentum Pseudo-Labeling for Semi-Supervised Speech Recognition},
    • booktitle = {Interspeech},
    • year = 2021,
    • pages = {726--730},
    • month = sep,
    • doi = {10.21437/Interspeech.2021-571},
    • url = {https://www.merl.com/publications/TR2021-103}
    • }
  •  Hori, T., Moritz, N., Hori, C., Le Roux, J., "Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers", Interspeech, DOI: 10.21437/​Interspeech.2021-1643, August 2021, pp. 2097-2101.
    BibTeX TR2021-100 PDF
    • @inproceedings{Hori2021aug3,
    • author = {Hori, Takaaki and Moritz, Niko and Hori, Chiori and Le Roux, Jonathan},
    • title = {Advanced Long-context End-to-end Speech Recognition Using Context-expanded Transformers},
    • booktitle = {Interspeech},
    • year = 2021,
    • pages = {2097--2101},
    • month = aug,
    • doi = {10.21437/Interspeech.2021-1643},
    • url = {https://www.merl.com/publications/TR2021-100}
    • }