NanoVoice: Efficient Speaker-Adaptive Text-to-Speech for Multiple Speakers
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_ | 1866917875881607168 |
|---|---|
| author | Park, Nohil Kim, Heeseung Lee, Che Hyun Choi, Jooyoung Yeom, Jiheum Yoon, Sungroh |
| author_facet | Park, Nohil Kim, Heeseung Lee, Che Hyun Choi, Jooyoung Yeom, Jiheum Yoon, Sungroh |
| contents | We present NanoVoice, a personalized text-to-speech model that efficiently constructs voice adapters for multiple speakers simultaneously. NanoVoice introduces a batch-wise speaker adaptation technique capable of fine-tuning multiple references in parallel, significantly reducing training time. Beyond building separate adapters for each speaker, we also propose a parameter sharing technique that reduces the number of parameters used for speaker adaptation. By incorporating a novel trainable scale matrix, NanoVoice mitigates potential performance degradation during parameter sharing. NanoVoice achieves performance comparable to the baselines, while training 4 times faster and using 45 percent fewer parameters for speaker adaptation with 40 reference voices. Extensive ablation studies and analysis further validate the efficiency of our model. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_15760 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | NanoVoice: Efficient Speaker-Adaptive Text-to-Speech for Multiple Speakers Park, Nohil Kim, Heeseung Lee, Che Hyun Choi, Jooyoung Yeom, Jiheum Yoon, Sungroh Sound Audio and Speech Processing We present NanoVoice, a personalized text-to-speech model that efficiently constructs voice adapters for multiple speakers simultaneously. NanoVoice introduces a batch-wise speaker adaptation technique capable of fine-tuning multiple references in parallel, significantly reducing training time. Beyond building separate adapters for each speaker, we also propose a parameter sharing technique that reduces the number of parameters used for speaker adaptation. By incorporating a novel trainable scale matrix, NanoVoice mitigates potential performance degradation during parameter sharing. NanoVoice achieves performance comparable to the baselines, while training 4 times faster and using 45 percent fewer parameters for speaker adaptation with 40 reference voices. Extensive ablation studies and analysis further validate the efficiency of our model. |
| title | NanoVoice: Efficient Speaker-Adaptive Text-to-Speech for Multiple Speakers |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.15760 |