https://scholars.lib.ntu.edu.tw/handle/123456789/558970
標題: | One-Shot Voice Conversion by Vector Quantization | 作者: | Wu, D.-Y. HUNG-YI LEE |
關鍵字: | disentangled representations; vector quantization; voice conversion | 公開日期: | 2020 | 卷: | 2020-May | 起(迄)頁: | 7734-7738 | 來源出版物: | ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings | 摘要: | In this paper, we propose a vector quantization (VQ) based one-shot voice conversion (VC) approach without any supervision on speaker label. We model the content embedding as a series of discrete codes and take the difference between quantize-before and quantize-after vector as the speaker embedding. We show that this approach has a strong ability to disentangle the content and speaker information with reconstruction loss only, and one-shot VC is thus achieved. © 2020 IEEE. |
URI: | https://www.scopus.com/inward/record.url?eid=2-s2.0-85089227176&partnerID=40&md5=250cdc69c2b513111c3181093ce099d7 https://scholars.lib.ntu.edu.tw/handle/123456789/558970 |
ISSN: | 15206149 | DOI: | 10.1109/ICASSP40776.2020.9053854 |
顯示於: | 電機工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。