{"ID":2881860,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.11326","arxiv_id":"2508.11326","title":"MoE-TTS: Enhancing Out-of-Domain Text Understanding for Description-based TTS via Mixture-of-Experts","abstract":"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/.","short_abstract":"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 understandin...","url_abs":"https://arxiv.org/abs/2508.11326","url_pdf":"https://arxiv.org/pdf/2508.11326v1","authors":"[\"Heyang Xue\",\"Xuchen Song\",\"Yu Tang\",\"Jianyu Chen\",\"Yanru Chen\",\"Yang Li\",\"Yahui Zhou\"]","published":"2025-08-15T08:53:56Z","proceeding":"eess.AS","tasks":"[\"eess.AS\",\"cs.SD\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}