Audio-Based Linguistic Feature Extraction for Enhancing Multi-lingual and Low-Resource Text-to-Speech
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912048062922752 |
|---|---|
| author | Kim, Youngjae Jeon, Yejin Lee, Gary Geunbae |
| author_facet | Kim, Youngjae Jeon, Yejin Lee, Gary Geunbae |
| contents | The difficulty of acquiring abundant, high-quality data, especially in multi-lingual contexts, has sparked interest in addressing low-resource scenarios. Moreover, current literature rely on fixed expressions from language IDs, which results in the inadequate learning of language representations, and the failure to generate speech in unseen languages. To address these challenges, we propose a novel method that directly extracts linguistic features from audio input while effectively filtering out miscellaneous acoustic information including speaker-specific attributes like timbre. Subjective and objective evaluations affirm the effectiveness of our approach for multi-lingual text-to-speech, and highlight its superiority in low-resource transfer learning for previously unseen language. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18622 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Audio-Based Linguistic Feature Extraction for Enhancing Multi-lingual and Low-Resource Text-to-Speech Kim, Youngjae Jeon, Yejin Lee, Gary Geunbae Sound Audio and Speech Processing The difficulty of acquiring abundant, high-quality data, especially in multi-lingual contexts, has sparked interest in addressing low-resource scenarios. Moreover, current literature rely on fixed expressions from language IDs, which results in the inadequate learning of language representations, and the failure to generate speech in unseen languages. To address these challenges, we propose a novel method that directly extracts linguistic features from audio input while effectively filtering out miscellaneous acoustic information including speaker-specific attributes like timbre. Subjective and objective evaluations affirm the effectiveness of our approach for multi-lingual text-to-speech, and highlight its superiority in low-resource transfer learning for previously unseen language. |
| title | Audio-Based Linguistic Feature Extraction for Enhancing Multi-lingual and Low-Resource Text-to-Speech |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2409.18622 |