SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912174124826624 |
|---|---|
| author | Wang, Helin Yu, Meng Hai, Jiarui Chen, Chen Hu, Yuchen Chen, Rilin Dehak, Najim Yu, Dong |
| author_facet | Wang, Helin Yu, Meng Hai, Jiarui Chen, Chen Hu, Yuchen Chen, Rilin Dehak, Najim Yu, Dong |
| contents | In this paper, we introduce SSR-Speech, a neural codec autoregressive model designed for stable, safe, and robust zero-shot textbased speech editing and text-to-speech synthesis. SSR-Speech is built on a Transformer decoder and incorporates classifier-free guidance to enhance the stability of the generation process. A watermark Encodec is proposed to embed frame-level watermarks into the edited regions of the speech so that which parts were edited can be detected. In addition, the waveform reconstruction leverages the original unedited speech segments, providing superior recovery compared to the Encodec model. Our approach achieves state-of-the-art performance in the RealEdit speech editing task and the LibriTTS text-to-speech task, surpassing previous methods. Furthermore, SSR-Speech excels in multi-span speech editing and also demonstrates remarkable robustness to background sounds. The source code and demos are released. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_07556 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis Wang, Helin Yu, Meng Hai, Jiarui Chen, Chen Hu, Yuchen Chen, Rilin Dehak, Najim Yu, Dong Audio and Speech Processing Sound In this paper, we introduce SSR-Speech, a neural codec autoregressive model designed for stable, safe, and robust zero-shot textbased speech editing and text-to-speech synthesis. SSR-Speech is built on a Transformer decoder and incorporates classifier-free guidance to enhance the stability of the generation process. A watermark Encodec is proposed to embed frame-level watermarks into the edited regions of the speech so that which parts were edited can be detected. In addition, the waveform reconstruction leverages the original unedited speech segments, providing superior recovery compared to the Encodec model. Our approach achieves state-of-the-art performance in the RealEdit speech editing task and the LibriTTS text-to-speech task, surpassing previous methods. Furthermore, SSR-Speech excels in multi-span speech editing and also demonstrates remarkable robustness to background sounds. The source code and demos are released. |
| title | SSR-Speech: Towards Stable, Safe and Robust Zero-shot Text-based Speech Editing and Synthesis |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2409.07556 |