Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.04708 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913462943219712 |
|---|---|
| author | Huang, Jiawei Zhang, Chen Ren, Yi Jiang, Ziyue Ye, Zhenhui Liu, Jinglin He, Jinzheng Yin, Xiang Zhao, Zhou |
| author_facet | Huang, Jiawei Zhang, Chen Ren, Yi Jiang, Ziyue Ye, Zhenhui Liu, Jinglin He, Jinzheng Yin, Xiang Zhao, Zhou |
| contents | Voice conversion aims to modify the source speaker's voice to resemble the target speaker while preserving the original speech content. Despite notable advancements in voice conversion these days, multi-lingual voice conversion (including both monolingual and cross-lingual scenarios) has yet to be extensively studied. It faces two main challenges: 1) the considerable variability in prosody and articulation habits across languages; and 2) the rarity of paired multi-lingual datasets from the same speaker. In this paper, we propose MulliVC, a novel voice conversion system that only converts timbre and keeps original content and source language prosody without multi-lingual paired data. Specifically, each training step of MulliVC contains three substeps: In step one the model is trained with monolingual speech data; then, steps two and three take inspiration from back translation, construct a cyclical process to disentangle the timbre and other information (content, prosody, and other language-related information) in the absence of multi-lingual data from the same speaker. Both objective and subjective results indicate that MulliVC significantly surpasses other methods in both monolingual and cross-lingual contexts, demonstrating the system's efficacy and the viability of the three-step approach with cycle consistency. Audio samples can be found on our demo page (mullivc.github.io). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_04708 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MulliVC: Multi-lingual Voice Conversion With Cycle Consistency Huang, Jiawei Zhang, Chen Ren, Yi Jiang, Ziyue Ye, Zhenhui Liu, Jinglin He, Jinzheng Yin, Xiang Zhao, Zhou Sound Artificial Intelligence Audio and Speech Processing Voice conversion aims to modify the source speaker's voice to resemble the target speaker while preserving the original speech content. Despite notable advancements in voice conversion these days, multi-lingual voice conversion (including both monolingual and cross-lingual scenarios) has yet to be extensively studied. It faces two main challenges: 1) the considerable variability in prosody and articulation habits across languages; and 2) the rarity of paired multi-lingual datasets from the same speaker. In this paper, we propose MulliVC, a novel voice conversion system that only converts timbre and keeps original content and source language prosody without multi-lingual paired data. Specifically, each training step of MulliVC contains three substeps: In step one the model is trained with monolingual speech data; then, steps two and three take inspiration from back translation, construct a cyclical process to disentangle the timbre and other information (content, prosody, and other language-related information) in the absence of multi-lingual data from the same speaker. Both objective and subjective results indicate that MulliVC significantly surpasses other methods in both monolingual and cross-lingual contexts, demonstrating the system's efficacy and the viability of the three-step approach with cycle consistency. Audio samples can be found on our demo page (mullivc.github.io). |
| title | MulliVC: Multi-lingual Voice Conversion With Cycle Consistency |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2408.04708 |