Hui Lu, Xixin Wu, Zhiyong Wu 0003, Helen Meng. SpeechTripleNet: End-to-End Disentangled Speech Representation Learning for Content, Timbre and Prosody. In Abdulmotaleb El-Saddik, Tao Mei, Rita Cucchiara, Marco Bertini 0001, Diana Patricia Tobon Vallejo, Pradeep K. Atrey, M. Shamim Hossain, editors, Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023. pages 2829-2837, ACM, 2023. [doi]
@inproceedings{LuW0M23,
title = {SpeechTripleNet: End-to-End Disentangled Speech Representation Learning for Content, Timbre and Prosody},
author = {Hui Lu and Xixin Wu and Zhiyong Wu 0003 and Helen Meng},
year = {2023},
doi = {10.1145/3581783.3612485},
url = {https://doi.org/10.1145/3581783.3612485},
researchr = {https://researchr.org/publication/LuW0M23},
cites = {0},
citedby = {0},
pages = {2829-2837},
booktitle = {Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023},
editor = {Abdulmotaleb El-Saddik and Tao Mei and Rita Cucchiara and Marco Bertini 0001 and Diana Patricia Tobon Vallejo and Pradeep K. Atrey and M. Shamim Hossain},
publisher = {ACM},
}