- 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}
- }
- 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}
- }
- 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}
- }
- Pan, Z., Wichern, G., Germain, F., Subramanian, A.S., Le Roux, J., "Towards End-to-end Speaker Diarization in the Wild", arXiv, November 2022.
BibTeX arXiv- @article{Pan2022nov,
- author = {Pan, Zexu and Wichern, Gordon and Germain, Francois and Subramanian, Aswin Shanmugam and {Le Roux}, Jonathan},
- title = {{Towards End-to-end Speaker Diarization in the Wild}},
- journal = {arXiv},
- year = 2022,
- month = nov,
- url = {https://arxiv.org/abs/2211.01299}
- }