Publications

169 / 3,803 publications found.


  •  Jeon, C.-B., Wichern, G., Germain, F.G., Le Roux, J., "Why does music source separation benefit from cacophony?", IEEE ICASSP Satellite Workshop on Explainable Machine Learning for Speech and Audio (XAI-SA), DOI: 10.1109/​ICASSPW62465.2024.10669899, March 2024, pp. 873-877.
    BibTeX TR2024-030 PDF Video
    • @inproceedings{Jeon2024mar,
    • author = {Jeon, Chang-Bin and Wichern, Gordon and Germain, François G and {Le Roux}, Jonathan},
    • title = {{Why does music source separation benefit from cacophony?}},
    • booktitle = {IEEE ICASSP Satellite Workshop on Explainable Machine Learning for Speech and Audio (XAI-SA)},
    • year = 2024,
    • pages = {873--877},
    • month = mar,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSPW62465.2024.10669899},
    • isbn = {979-8-3503-7451-3},
    • url = {https://www.merl.com/publications/TR2024-030}
    • }
  •  Bralios, D., Wichern, G., Germain, F.G., Pan, Z., Khurana, S., Hori, C., Le Roux, J., "Generation or Replication: Auscultating Audio Latent Diffusion Models", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP48485.2024.10447705, March 2024, pp. 1156-1160.
    BibTeX TR2024-027 PDF
    • @inproceedings{Bralios2024mar,
    • author = {Bralios, Dimitrios and Wichern, Gordon and Germain, François G and Pan, Zexu and Khurana, Sameer and Hori, Chiori and {Le Roux}, Jonathan},
    • title = {{Generation or Replication: Auscultating Audio Latent Diffusion Models}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2024,
    • pages = {1156--1160},
    • month = mar,
    • doi = {10.1109/ICASSP48485.2024.10447705},
    • url = {https://www.merl.com/publications/TR2024-027}
    • }
  •  Masuyama, Y., Wichern, G., Germain, F.G., Pan, Z., Khurana, S., Hori, C., Le Roux, J., "NIIRF: Neural IIR Filter Field for HRTF Upsampling and Personalization", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP48485.2024.10448477, March 2024, pp. 1016-1020.
    BibTeX TR2024-026 PDF Software
    • @inproceedings{Masuyama2024mar,
    • author = {Masuyama, Yoshiki and Wichern, Gordon and Germain, François G and Pan, Zexu and Khurana, Sameer and Hori, Chiori and {Le Roux}, Jonathan},
    • title = {{NIIRF: Neural IIR Filter Field for HRTF Upsampling and Personalization}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2024,
    • pages = {1016--1020},
    • month = mar,
    • doi = {10.1109/ICASSP48485.2024.10448477},
    • url = {https://www.merl.com/publications/TR2024-026}
    • }
  •  Pan, Z., Wichern, G., Germain, F.G., Khurana, S., Le Roux, J., "NeuroHeed+: Improving Neuro-steered Speaker Extraction with Joint Auditory Attention Detection", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP48485.2024.10446333, March 2024, pp. 11456-11460.
    BibTeX TR2024-025 PDF
    • @inproceedings{Pan2024mar,
    • author = {Pan, Zexu and Wichern, Gordon and Germain, François G and Khurana, Sameer and {Le Roux}, Jonathan},
    • title = {{NeuroHeed+: Improving Neuro-steered Speaker Extraction with Joint Auditory Attention Detection}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2024,
    • pages = {11456--11460},
    • month = mar,
    • doi = {10.1109/ICASSP48485.2024.10446333},
    • url = {https://www.merl.com/publications/TR2024-025}
    • }
  •  Wu, S.-L., Chang, X., Wichern, G., Jung, J.-W., Germain, F.G., Le Roux, J., Watanabe, S., "Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP48485.2024.10447215, March 2024, pp. 316-320.
    BibTeX TR2024-028 PDF
    • @inproceedings{Wu2024mar,
    • author = {Wu, Shih-Lun and Chang, Xuankai and Wichern, Gordon and Jung, Jee-weon and Germain, François G and {Le Roux}, Jonathan and Watanabe, Shinji},
    • title = {{Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up Augmentation}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2024,
    • pages = {316--320},
    • month = mar,
    • doi = {10.1109/ICASSP48485.2024.10447215},
    • url = {https://www.merl.com/publications/TR2024-028}
    • }
  •  Baoueb, T., Liu, H., Fontaine, M., Le Roux, J., Richard, G., "SpecDiff-GAN: A Spectrally-Shaped Noise Diffusion GAN for Speech and Music Synthesis", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP48485.2024.10446830, March 2024, pp. 986-990.
    BibTeX TR2024-013 PDF
    • @inproceedings{Baoueb2024mar,
    • author = {Baoueb, Teysir and Liu, Haocheng and Fontaine, Mathieu and {Le Roux}, Jonathan and Richard, Gaël},
    • title = {{SpecDiff-GAN: A Spectrally-Shaped Noise Diffusion GAN for Speech and Music Synthesis}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2024,
    • pages = {986--990},
    • month = mar,
    • doi = {10.1109/ICASSP48485.2024.10446830},
    • issn = {2379-190X},
    • isbn = {979-8-3503-4485-1},
    • url = {https://www.merl.com/publications/TR2024-013}
    • }
  •  Hori, C., Wang, P., Rahman, M., Vaca-Rubio, C., Khurana, S., Cherian, A., Le Roux, J., "Wi-Fi based Indoor Monitoring Enhanced by Multimodal Fusion", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP48485.2024.10447600, March 2024, pp. 13296-13300.
    BibTeX TR2024-012 PDF
    • @inproceedings{Hori2024mar,
    • author = {Hori, Chiori and Wang, Pu and Rahman, Mahbub and Vaca-Rubio, Cristian and Khurana, Sameer and Cherian, Anoop and {Le Roux}, Jonathan},
    • title = {{Wi-Fi based Indoor Monitoring Enhanced by Multimodal Fusion}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2024,
    • pages = {13296--13300},
    • month = mar,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP48485.2024.10447600},
    • issn = {2379-190X},
    • isbn = {979-8-3503-4485-1},
    • url = {https://www.merl.com/publications/TR2024-012}
    • }
  •  Liu, H., Baoueb, T., Fontaine, M., Le Roux, J., Richard, G., "GLA-Grad: A Griffin-Lim Extended Waveform Generation Diffusion Model", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP48485.2024.10446058, March 2024, pp. 11611-11615.
    BibTeX TR2024-014 PDF
    • @inproceedings{Liu2024mar,
    • author = {Liu, Haocheng and Baoueb, Teysir and Fontaine, Mathieu and {Le Roux}, Jonathan and Richard, Gaël},
    • title = {{GLA-Grad: A Griffin-Lim Extended Waveform Generation Diffusion Model}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2024,
    • pages = {11611--11615},
    • month = mar,
    • doi = {10.1109/ICASSP48485.2024.10446058},
    • issn = {2379-190X},
    • isbn = {979-8-3503-4485-1},
    • url = {https://www.merl.com/publications/TR2024-014}
    • }
  •  Boeddeker, C., Subramanian, A.S., Wichern, G., Haeb-Umbach, R., Le Roux, J., "TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings", IEEE/ACM Transactions on Audio, Speech, and Language Processing, DOI: 10.1109/​TASLP.2024.3350887, Vol. 32, pp. 1185-1197, February 2024.
    BibTeX TR2024-006 PDF Software
    • @article{Boeddeker2024feb,
    • author = {Boeddeker, Christoph and Subramanian, Aswin Shanmugam and Wichern, Gordon and Haeb-Umbach, Reinhold and {Le Roux}, Jonathan},
    • title = {{TS-SEP: Joint Diarization and Separation Conditioned on Estimated Speaker Embeddings}},
    • journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    • year = 2024,
    • volume = 32,
    • pages = {1185--1197},
    • month = feb,
    • doi = {10.1109/TASLP.2024.3350887},
    • issn = {2329-9304},
    • url = {https://www.merl.com/publications/TR2024-006}
    • }
  •  Pan, Z., Wichern, G., Masuyama, Y., Germain, F.G., Khurana, S., Hori, C., Le Roux, J., "Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction", IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU), DOI: 10.1109/​ASRU57964.2023.10389618, December 2023.
    BibTeX TR2023-152 PDF Video
    • @inproceedings{Pan2023dec2,
    • author = {Pan, Zexu and Wichern, Gordon and Masuyama, Yoshiki and Germain, François G and Khurana, Sameer and Hori, Chiori and {Le Roux}, Jonathan},
    • title = {{Scenario-Aware Audio-Visual TF-GridNet for Target Speech Extraction}},
    • booktitle = {IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)},
    • year = 2023,
    • month = dec,
    • doi = {10.1109/ASRU57964.2023.10389618},
    • isbn = {979-8-3503-0689-7},
    • url = {https://www.merl.com/publications/TR2023-152}
    • }
  •  Wu, S.-L., Chang, X., Wichern, G., Jung, J.-W., Germain, F.G., Le Roux, J., Watanabe, S., "On the Use of Pretrained Deep Audio Encoders for Automated Audio Captioning Tasks", International Symposium on Future Active Safety Technology toward zero traffic accidents (FAST-zero), November 2023.
    BibTeX TR2023-141 PDF
    • @inproceedings{Wu2023nov,
    • author = {Wu, Shih-Lun and Chang, Xuankai and Wichern, Gordon and Jung, Jee-weon and Germain, François G and {Le Roux}, Jonathan and Watanabe, Shinji},
    • title = {{On the Use of Pretrained Deep Audio Encoders for Automated Audio Captioning Tasks}},
    • booktitle = {International Symposium on Future Active Safety Technology toward zero traffic accidents (FAST-zero)},
    • year = 2023,
    • month = nov,
    • url = {https://www.merl.com/publications/TR2023-141}
    • }
  •  Pan, Z., Wichern, G., Germain, F., Subramanian, A., Le Roux, J., "Late Audio-Visual Fusion for In-The-Wild Speaker Diarization", arXiv, DOI: 10.48550/​arXiv.2211.01299, September 2023.
    BibTeX arXiv
    • @article{Pan2023sep,
    • author = {Pan, Zexu and Wichern, Gordon and Germain, Francois and Subramanian, Aswin and {Le Roux}, Jonathan},
    • title = {{Late Audio-Visual Fusion for In-The-Wild Speaker Diarization}},
    • journal = {arXiv},
    • year = 2023,
    • month = sep,
    • doi = {10.48550/arXiv.2211.01299},
    • url = {https://arxiv.org/abs/2211.01299}
    • }
  •  Falcon Perez, R., Wichern, G., Germain, F., Le Roux, J., "Location as supervision for weakly supervised multi-channel source separation of machine sounds", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), DOI: 10.1109/​WASPAA58266.2023.10248128, September 2023.
    BibTeX TR2023-119 PDF Presentation
    • @inproceedings{FalconPerez2023aug,
    • author = {Falcon Perez, Ricardo and Wichern, Gordon and Germain, Francois and {Le Roux}, Jonathan},
    • title = {{Location as supervision for weakly supervised multi-channel source separation of machine sounds}},
    • booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
    • year = 2023,
    • month = sep,
    • publisher = {IEEE},
    • doi = {10.1109/WASPAA58266.2023.10248128},
    • issn = {1947-1629},
    • isbn = {979-8-3503-2372-6},
    • url = {https://www.merl.com/publications/TR2023-119}
    • }
  •  Germain, F., Wichern, G., Le Roux, J., "Hyperbolic Unsupervised Anomalous Sound Detection", IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), DOI: 10.1109/​WASPAA58266.2023.10248092, September 2023.
    BibTeX TR2023-108 PDF Video Presentation
    • @inproceedings{Germain2023aug,
    • author = {Germain, Francois and Wichern, Gordon and {Le Roux}, Jonathan},
    • title = {{Hyperbolic Unsupervised Anomalous Sound Detection}},
    • booktitle = {IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)},
    • year = 2023,
    • month = sep,
    • publisher = {IEEE},
    • doi = {10.1109/WASPAA58266.2023.10248092},
    • issn = {1947-1629},
    • isbn = {979-8-3503-2372-6},
    • url = {https://www.merl.com/publications/TR2023-108}
    • }
  •  Petermann, D., Wichern, G., Subramanian, A.S., Wang, Z.-Q., Le Roux, J., "Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks", IEEE/ACM Transactions on Audio, Speech, and Language Processing, DOI: 10.1109/​TASLP.2023.3290428, Vol. 31, pp. 2592-2605, September 2023.
    BibTeX TR2023-113 PDF
    • @article{Petermann2023sep,
    • author = {Petermann, Darius and Wichern, Gordon and Subramanian, Aswin Shanmugam and Wang, Zhong-Qiu and {Le Roux}, Jonathan},
    • title = {{Tackling the Cocktail Fork Problem for Separation and Transcription of Real-World Soundtracks}},
    • journal = {IEEE/ACM Transactions on Audio, Speech, and Language Processing},
    • year = 2023,
    • volume = 31,
    • pages = {2592--2605},
    • month = sep,
    • doi = {10.1109/TASLP.2023.3290428},
    • issn = {2329-9304},
    • url = {https://www.merl.com/publications/TR2023-113}
    • }
  •  Hori, C., Peng, P., Harwath, D., Liu, X., Ota, K., Jain, S., Corcodel, R., Jha, D.K., Romeres, D., Le Roux, J., "Style-transfer based Speech and Audio-visual Scene understanding for Robot Action Sequence Acquisition from Videos", Interspeech, DOI: 10.21437/​Interspeech.2023-1983, August 2023, pp. 4663-4667.
    BibTeX TR2023-104 PDF
    • @inproceedings{Hori2023aug,
    • author = {Hori, Chiori and Peng, Puyuang and Harwath, David and Liu, Xinyu and Ota, Kei and Jain, Siddarth and Corcodel, Radu and Jha, Devesh K. and Romeres, Diego and {Le Roux}, Jonathan},
    • title = {{Style-transfer based Speech and Audio-visual Scene understanding for Robot Action Sequence Acquisition from Videos}},
    • booktitle = {Interspeech},
    • year = 2023,
    • pages = {4663--4667},
    • month = aug,
    • doi = {10.21437/Interspeech.2023-1983},
    • url = {https://www.merl.com/publications/TR2023-104}
    • }
  •  Wu, S.-L., Chang, X., Wichern, G., Jung, J.-W., Germain, F., Le Roux, J., Watanabe, S., "BEATs-based Audio Captioning Model with Instructor Embedding Supervision and ChatGPT Mix-up," Tech. Rep. TR2023-068, DCASE2023 Challenge, May 2023.
    BibTeX TR2023-068 PDF
    • @techreport{Wu2023may,
    • author = {Wu, Shih-Lun and Chang, Xuankai and Wichern, Gordon and Jung, Jee-weon and Germain, Francois and {Le Roux}, Jonathan and Watanabe, Shinji},
    • title = {{BEATs-based Audio Captioning Model with Instructor Embedding Supervision and ChatGPT Mix-up}},
    • institution = {DCASE2023 Challenge},
    • year = 2023,
    • month = may,
    • url = {https://www.merl.com/publications/TR2023-068}
    • }
  •  Chen, K., Wichern, G., Germain, F., Le Roux, J., "Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT", IEEE ICASSP Satellite Workshop on Self-supervision in Audio, Speech and Beyond (SASB), DOI: 10.1109/​ICASSPW59220.2023.10193575, May 2023.
    BibTeX TR2023-030 PDF
    • @inproceedings{Chen2023may,
    • author = {Chen, Ke and Wichern, Gordon and Germain, Francois and {Le Roux}, Jonathan},
    • title = {{Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERT}},
    • booktitle = {IEEE ICASSP Satellite Workshop on Self-supervision in Audio, Speech and Beyond (SASB)},
    • year = 2023,
    • month = may,
    • doi = {10.1109/ICASSPW59220.2023.10193575},
    • isbn = {979-8-3503-0261-5},
    • url = {https://www.merl.com/publications/TR2023-030}
    • }
  •  Aralikatti, R., Boeddeker, C., Wichern, G., Subramanian, A.S., Le Roux, J., "Reverberation as Supervision for Speech Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10095022, May 2023, pp. 1-5.
    BibTeX TR2023-016 PDF
    • @inproceedings{Aralikatti2023may,
    • author = {Aralikatti, Rohith and Boeddeker, Christoph and Wichern, Gordon and Subramanian, Aswin Shanmugam and {Le Roux}, Jonathan},
    • title = {{Reverberation as Supervision for Speech Separation}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10095022},
    • url = {https://www.merl.com/publications/TR2023-016}
    • }
  •  Bralios, D., Tzinis, E., Wichern, G., Smaragdis, P., Le Roux, J., "Latent Iterative Refinement for Modular Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10096897, May 2023, pp. 1-5.
    BibTeX TR2023-019 PDF
    • @inproceedings{Bralios2023may,
    • author = {Bralios, Dimitrios and Tzinis, Efthymios and Wichern, Gordon and Smaragdis, Paris and {Le Roux}, Jonathan},
    • title = {{Latent Iterative Refinement for Modular Source Separation}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10096897},
    • url = {https://www.merl.com/publications/TR2023-019}
    • }
  •  Petermann, D., Wichern, G., Subramanian, A.S., Le Roux, J., "Hyperbolic Audio Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10094943, May 2023, pp. 1-5.
    BibTeX TR2023-017 PDF Video Software
    • @inproceedings{Petermann2023may,
    • author = {Petermann, Darius and Wichern, Gordon and Subramanian, Aswin Shanmugam and {Le Roux}, Jonathan},
    • title = {{Hyperbolic Audio Source Separation}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10094943},
    • url = {https://www.merl.com/publications/TR2023-017}
    • }
  •  Tzinis, E., Wichern, G., Smaragdis, P., Le Roux, J., "Optimal Condition Training for Target Source Separation", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10095128, May 2023, pp. 1-5.
    BibTeX TR2023-018 PDF
    • @inproceedings{Tzinis2023may,
    • author = {Tzinis, Efthymios and Wichern, Gordon and Smaragdis, Paris and {Le Roux}, Jonathan},
    • title = {{Optimal Condition Training for Target Source Separation}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10095128},
    • url = {https://www.merl.com/publications/TR2023-018}
    • }
  •  Yen, H., Germain, F., Wichern, G., Le Roux, J., "Cold Diffusion for Speech Enhancement", IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), DOI: 10.1109/​ICASSP49357.2023.10096064, May 2023, pp. 1-5.
    BibTeX TR2023-020 PDF
    • @inproceedings{Yen2023may,
    • author = {Yen, Hao and Germain, Francois and Wichern, Gordon and {Le Roux}, Jonathan},
    • title = {{Cold Diffusion for Speech Enhancement}},
    • booktitle = {IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP)},
    • year = 2023,
    • pages = {1--5},
    • month = may,
    • publisher = {IEEE},
    • doi = {10.1109/ICASSP49357.2023.10096064},
    • url = {https://www.merl.com/publications/TR2023-020}
    • }
  •  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, DOI: 10.1109/​TASLP.2022.3224285, Vol. 31, pp. 397-410, 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,
    • volume = 31,
    • pages = {397--410},
    • month = dec,
    • doi = {10.1109/TASLP.2022.3224285},
    • issn = {2329-9304},
    • 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}
    • }