MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916901347655680 |
|---|---|
| author | Xue, Heyang Song, Xuchen Tang, Yu Chen, Jianyu Chen, Yanru Li, Yang Zhou, Yahui |
| author_facet | Xue, Heyang Song, Xuchen Tang, Yu Chen, Jianyu Chen, Yanru Li, Yang Zhou, Yahui |
| contents | Description-based text-to-speech (TTS) models exhibit strong performance on in-domain text descriptions, i.e., those encountered during training. However, in real-world applications, the diverse range of user-generated descriptions inevitably introduces numerous out-of-domain inputs that challenge the text understanding capabilities of these systems. To address this issue, we propose MoE-TTS, a description-based TTS model designed to enhance the understanding of out-of-domain text descriptions. MoE-TTS employs a modality-based mixture-of-experts (MoE) approach to augment a pre-trained textual large language model (LLM) with a set of specialized weights adapted to the speech modality while maintaining the original LLM frozen during training. This approach allows MoE-TTS to effectively leverage the pre-trained knowledge and text understanding abilities of textual LLMs. Our experimental results indicate that: first, even the most advanced closed-source commercial products can be challenged by carefully designed out-of-domain description test sets; second, MoE-TTS achieves superior performance in generating speech that more accurately reflects the descriptions. We encourage readers to listen to the demos at https://welkinyang.github.io/MoE-TTS/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_11326 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts Xue, Heyang Song, Xuchen Tang, Yu Chen, Jianyu Chen, Yanru Li, Yang Zhou, Yahui Audio and Speech Processing Sound Description-based text-to-speech (TTS) models exhibit strong performance on in-domain text descriptions, i.e., those encountered during training. However, in real-world applications, the diverse range of user-generated descriptions inevitably introduces numerous out-of-domain inputs that challenge the text understanding capabilities of these systems. To address this issue, we propose MoE-TTS, a description-based TTS model designed to enhance the understanding of out-of-domain text descriptions. MoE-TTS employs a modality-based mixture-of-experts (MoE) approach to augment a pre-trained textual large language model (LLM) with a set of specialized weights adapted to the speech modality while maintaining the original LLM frozen during training. This approach allows MoE-TTS to effectively leverage the pre-trained knowledge and text understanding abilities of textual LLMs. Our experimental results indicate that: first, even the most advanced closed-source commercial products can be challenged by carefully designed out-of-domain description test sets; second, MoE-TTS achieves superior performance in generating speech that more accurately reflects the descriptions. We encourage readers to listen to the demos at https://welkinyang.github.io/MoE-TTS/. |
| title | MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2508.11326 |