CNEG-VC: Contrastive Learning Using Hard Negative Example In Non-Parallel Voice Conversion

Bima Prihasto, Yi Xing Lin, Phuong Thi Le, Chien Lin Huang, Jia Ching Wang

研究成果: 書貢獻/報告類型會議論文篇章同行評審

3 引文 斯高帕斯(Scopus)

摘要

Contrastive learning has advantages for non-parallel voice conversion, but the previous conversion results could be better and more preserved. In previous techniques, negative samples were randomly selected in the features vector from different locations. A positive example could not be effectively pushed toward the query examples. We present contrastive learning in non-parallel voice conversion to solve this problem using hard negative examples. We named it CNEG-VC. Specifically, we teach the generator to generate negative examples. Our proposed generator has specific features. First, Instance-wise negative examples are generated based on voice input. Second, when taught with an adversarial loss, it can produce hard negative examples. The generator significantly improves non-parallel voice conversion performance. Our CNEG-VC achieved state-of-the-art results by outperforming previous techniques.

原文???core.languages.en_GB???
主出版物標題ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, Proceedings
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781728163277
DOIs
出版狀態已出版 - 2023
事件48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023 - Rhodes Island, Greece
持續時間: 4 6月 202310 6月 2023

出版系列

名字ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
2023-June
ISSN(列印)1520-6149

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023
國家/地區Greece
城市Rhodes Island
期間4/06/2310/06/23

指紋

深入研究「CNEG-VC: Contrastive Learning Using Hard Negative Example In Non-Parallel Voice Conversion」主題。共同形成了獨特的指紋。

引用此