The THU-HCSI Multi-Speaker Multi-Lingual Few-Shot Voice Cloning System for LIMMITS'24 Challenge
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917650418892800 |
|---|---|
| author | Zhou, Yixuan Zhou, Shuoyi Lei, Shun Wu, Zhiyong Wu, Menglin |
| author_facet | Zhou, Yixuan Zhou, Shuoyi Lei, Shun Wu, Zhiyong Wu, Menglin |
| contents | This paper presents the multi-speaker multi-lingual few-shot voice cloning system developed by THU-HCSI team for LIMMITS'24 Challenge. To achieve high speaker similarity and naturalness in both mono-lingual and cross-lingual scenarios, we build the system upon YourTTS and add several enhancements. For further improving speaker similarity and speech quality, we introduce speaker-aware text encoder and flow-based decoder with Transformer blocks. In addition, we denoise the few-shot data, mix up them with pre-training data, and adopt a speaker-balanced sampling strategy to guarantee effective fine-tuning for target speakers. The official evaluations in track 1 show that our system achieves the best speaker similarity MOS of 4.25 and obtains considerable naturalness MOS of 3.97. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_16619 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The THU-HCSI Multi-Speaker Multi-Lingual Few-Shot Voice Cloning System for LIMMITS'24 Challenge Zhou, Yixuan Zhou, Shuoyi Lei, Shun Wu, Zhiyong Wu, Menglin Sound Audio and Speech Processing This paper presents the multi-speaker multi-lingual few-shot voice cloning system developed by THU-HCSI team for LIMMITS'24 Challenge. To achieve high speaker similarity and naturalness in both mono-lingual and cross-lingual scenarios, we build the system upon YourTTS and add several enhancements. For further improving speaker similarity and speech quality, we introduce speaker-aware text encoder and flow-based decoder with Transformer blocks. In addition, we denoise the few-shot data, mix up them with pre-training data, and adopt a speaker-balanced sampling strategy to guarantee effective fine-tuning for target speakers. The official evaluations in track 1 show that our system achieves the best speaker similarity MOS of 4.25 and obtains considerable naturalness MOS of 3.97. |
| title | The THU-HCSI Multi-Speaker Multi-Lingual Few-Shot Voice Cloning System for LIMMITS'24 Challenge |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2404.16619 |