SelfVC: Voice Conversion With Iterative Refinement using Self Transformations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866929334383542272 |
|---|---|
| author | Neekhara, Paarth Hussain, Shehzeen Valle, Rafael Ginsburg, Boris Ranjan, Rishabh Dubnov, Shlomo Koushanfar, Farinaz McAuley, Julian |
| author_facet | Neekhara, Paarth Hussain, Shehzeen Valle, Rafael Ginsburg, Boris Ranjan, Rishabh Dubnov, Shlomo Koushanfar, Farinaz McAuley, Julian |
| contents | We propose SelfVC, a training strategy to iteratively improve a voice conversion model with self-synthesized examples. Previous efforts on voice conversion focus on factorizing speech into explicitly disentangled representations that separately encode speaker characteristics and linguistic content. However, disentangling speech representations to capture such attributes using task-specific loss terms can lead to information loss. In this work, instead of explicitly disentangling attributes with loss terms, we present a framework to train a controllable voice conversion model on entangled speech representations derived from self-supervised learning (SSL) and speaker verification models. First, we develop techniques to derive prosodic information from the audio signal and SSL representations to train predictive submodules in the synthesis model. Next, we propose a training strategy to iteratively improve the synthesis model for voice conversion, by creating a challenging training objective using self-synthesized examples. We demonstrate that incorporating such self-synthesized examples during training improves the speaker similarity of generated speech as compared to a baseline voice conversion model trained solely on heuristically perturbed inputs. Our framework is trained without any text and achieves state-of-the-art results in zero-shot voice conversion on metrics evaluating naturalness, speaker similarity, and intelligibility of synthesized audio. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_09653 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | SelfVC: Voice Conversion With Iterative Refinement using Self Transformations Neekhara, Paarth Hussain, Shehzeen Valle, Rafael Ginsburg, Boris Ranjan, Rishabh Dubnov, Shlomo Koushanfar, Farinaz McAuley, Julian Sound Artificial Intelligence Audio and Speech Processing We propose SelfVC, a training strategy to iteratively improve a voice conversion model with self-synthesized examples. Previous efforts on voice conversion focus on factorizing speech into explicitly disentangled representations that separately encode speaker characteristics and linguistic content. However, disentangling speech representations to capture such attributes using task-specific loss terms can lead to information loss. In this work, instead of explicitly disentangling attributes with loss terms, we present a framework to train a controllable voice conversion model on entangled speech representations derived from self-supervised learning (SSL) and speaker verification models. First, we develop techniques to derive prosodic information from the audio signal and SSL representations to train predictive submodules in the synthesis model. Next, we propose a training strategy to iteratively improve the synthesis model for voice conversion, by creating a challenging training objective using self-synthesized examples. We demonstrate that incorporating such self-synthesized examples during training improves the speaker similarity of generated speech as compared to a baseline voice conversion model trained solely on heuristically perturbed inputs. Our framework is trained without any text and achieves state-of-the-art results in zero-shot voice conversion on metrics evaluating naturalness, speaker similarity, and intelligibility of synthesized audio. |
| title | SelfVC: Voice Conversion With Iterative Refinement using Self Transformations |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2310.09653 |