RSET: Remapping-based Sorting Method for Emotion Transfer Speech Synthesis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914813383278592 |
|---|---|
| author | Shi, Haoxiang Wang, Jianzong Zhang, Xulong Cheng, Ning Yu, Jun Xiao, Jing |
| author_facet | Shi, Haoxiang Wang, Jianzong Zhang, Xulong Cheng, Ning Yu, Jun Xiao, Jing |
| contents | Although current Text-To-Speech (TTS) models are able to generate high-quality speech samples, there are still challenges in developing emotion intensity controllable TTS. Most existing TTS models achieve emotion intensity control by extracting intensity information from reference speeches. Unfortunately, limited by the lack of modeling for intra-class emotion intensity and the model's information decoupling capability, the generated speech cannot achieve fine-grained emotion intensity control and suffers from information leakage issues. In this paper, we propose an emotion transfer TTS model, which defines a remapping-based sorting method to model intra-class relative intensity information, combined with Mutual Information (MI) to decouple speaker and emotion information, and synthesizes expressive speeches with perceptible intensity differences. Experiments show that our model achieves fine-grained emotion control while preserving speaker information. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_17028 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RSET: Remapping-based Sorting Method for Emotion Transfer Speech Synthesis Shi, Haoxiang Wang, Jianzong Zhang, Xulong Cheng, Ning Yu, Jun Xiao, Jing Sound Audio and Speech Processing Although current Text-To-Speech (TTS) models are able to generate high-quality speech samples, there are still challenges in developing emotion intensity controllable TTS. Most existing TTS models achieve emotion intensity control by extracting intensity information from reference speeches. Unfortunately, limited by the lack of modeling for intra-class emotion intensity and the model's information decoupling capability, the generated speech cannot achieve fine-grained emotion intensity control and suffers from information leakage issues. In this paper, we propose an emotion transfer TTS model, which defines a remapping-based sorting method to model intra-class relative intensity information, combined with Mutual Information (MI) to decouple speaker and emotion information, and synthesizes expressive speeches with perceptible intensity differences. Experiments show that our model achieves fine-grained emotion control while preserving speaker information. |
| title | RSET: Remapping-based Sorting Method for Emotion Transfer Speech Synthesis |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2405.17028 |