Meta Learning Text-to-Speech Synthesis in over 7000 Languages
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_ | 1866910480050683904 |
|---|---|
| author | Lux, Florian Meyer, Sarina Behringer, Lyonel Zalkow, Frank Do, Phat Coler, Matt Habets, Emanuël A. P. Vu, Ngoc Thang |
| author_facet | Lux, Florian Meyer, Sarina Behringer, Lyonel Zalkow, Frank Do, Phat Coler, Matt Habets, Emanuël A. P. Vu, Ngoc Thang |
| contents | In this work, we take on the challenging task of building a single text-to-speech synthesis system that is capable of generating speech in over 7000 languages, many of which lack sufficient data for traditional TTS development. By leveraging a novel integration of massively multilingual pretraining and meta learning to approximate language representations, our approach enables zero-shot speech synthesis in languages without any available data. We validate our system's performance through objective measures and human evaluation across a diverse linguistic landscape. By releasing our code and models publicly, we aim to empower communities with limited linguistic resources and foster further innovation in the field of speech technology. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_06403 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Meta Learning Text-to-Speech Synthesis in over 7000 Languages Lux, Florian Meyer, Sarina Behringer, Lyonel Zalkow, Frank Do, Phat Coler, Matt Habets, Emanuël A. P. Vu, Ngoc Thang Computation and Language Machine Learning Sound Audio and Speech Processing In this work, we take on the challenging task of building a single text-to-speech synthesis system that is capable of generating speech in over 7000 languages, many of which lack sufficient data for traditional TTS development. By leveraging a novel integration of massively multilingual pretraining and meta learning to approximate language representations, our approach enables zero-shot speech synthesis in languages without any available data. We validate our system's performance through objective measures and human evaluation across a diverse linguistic landscape. By releasing our code and models publicly, we aim to empower communities with limited linguistic resources and foster further innovation in the field of speech technology. |
| title | Meta Learning Text-to-Speech Synthesis in over 7000 Languages |
| topic | Computation and Language Machine Learning Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.06403 |