EE-TTS: Emphatic Expressive TTS with Linguistic Information
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913856131956736 |
|---|---|
| author | Zhong, Yi Zhang, Chen Liu, Xule Sun, Chenxi Deng, Weishan Hu, Haifeng Sun, Zhongqian |
| author_facet | Zhong, Yi Zhang, Chen Liu, Xule Sun, Chenxi Deng, Weishan Hu, Haifeng Sun, Zhongqian |
| contents | While Current TTS systems perform well in synthesizing high-quality speech, producing highly expressive speech remains a challenge. Emphasis, as a critical factor in determining the expressiveness of speech, has attracted more attention nowadays. Previous works usually enhance the emphasis by adding intermediate features, but they can not guarantee the overall expressiveness of the speech. To resolve this matter, we propose Emphatic Expressive TTS (EE-TTS), which leverages multi-level linguistic information from syntax and semantics. EE-TTS contains an emphasis predictor that can identify appropriate emphasis positions from text and a conditioned acoustic model to synthesize expressive speech with emphasis and linguistic information. Experimental results indicate that EE-TTS outperforms baseline with MOS improvements of 0.49 and 0.67 in expressiveness and naturalness. EE-TTS also shows strong generalization across different datasets according to AB test results. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_12107 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | EE-TTS: Emphatic Expressive TTS with Linguistic Information Zhong, Yi Zhang, Chen Liu, Xule Sun, Chenxi Deng, Weishan Hu, Haifeng Sun, Zhongqian Sound Computation and Language Audio and Speech Processing While Current TTS systems perform well in synthesizing high-quality speech, producing highly expressive speech remains a challenge. Emphasis, as a critical factor in determining the expressiveness of speech, has attracted more attention nowadays. Previous works usually enhance the emphasis by adding intermediate features, but they can not guarantee the overall expressiveness of the speech. To resolve this matter, we propose Emphatic Expressive TTS (EE-TTS), which leverages multi-level linguistic information from syntax and semantics. EE-TTS contains an emphasis predictor that can identify appropriate emphasis positions from text and a conditioned acoustic model to synthesize expressive speech with emphasis and linguistic information. Experimental results indicate that EE-TTS outperforms baseline with MOS improvements of 0.49 and 0.67 in expressiveness and naturalness. EE-TTS also shows strong generalization across different datasets according to AB test results. |
| title | EE-TTS: Emphatic Expressive TTS with Linguistic Information |
| topic | Sound Computation and Language Audio and Speech Processing |
| url | https://arxiv.org/abs/2305.12107 |