Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2508.12001 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916059827666944 |
|---|---|
| author | Meng, Qingliang Deng, Yuqing Liang, Wei Yu, Limei Liang, Huizhi Li, Tian |
| author_facet | Meng, Qingliang Deng, Yuqing Liang, Wei Yu, Limei Liang, Huizhi Li, Tian |
| contents | Current non-autoregressive (NAR) text-to-speech (TTS) systems still struggle to model diverse and speaker-dependent duration variation. We further observe that richer duration variation can increase the synthesis difficulty of existing HiFi-GAN-based vocoders, leading to spectral artifacts and unstable time-frequency structures. To address these issues, we propose FNH-TTS, a VITS-based end-to-end TTS system with Mixture-of-Experts duration modeling and robust vocoder-side synthesis. Specifically, we introduce a Mixture-of-Experts Duration Predictor (MoE-DP) to capture diverse phoneme duration patterns and speaker-dependent speaking-rate characteristics. To convert richer duration variation into stable waveform generation, we further integrate a VOCOS-style vocoder with Collaborative Multi-Band and Sub-Band Discriminators. Experiments on LJSpeech, VCTK, and LibriTTS show that FNH-TTS achieves improved synthesis quality, duration-category accuracy, vocoder reconstruction quality, and inference efficiency. Further analysis shows that MoE-DP is the main source of improved duration modeling, while stronger vocoder-side components are necessary for robust synthesis under richer duration variation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_12001 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FNH-TTS: Mixture-of-Experts Duration Modeling for Robust Neural Speech Synthesis Meng, Qingliang Deng, Yuqing Liang, Wei Yu, Limei Liang, Huizhi Li, Tian Audio and Speech Processing Current non-autoregressive (NAR) text-to-speech (TTS) systems still struggle to model diverse and speaker-dependent duration variation. We further observe that richer duration variation can increase the synthesis difficulty of existing HiFi-GAN-based vocoders, leading to spectral artifacts and unstable time-frequency structures. To address these issues, we propose FNH-TTS, a VITS-based end-to-end TTS system with Mixture-of-Experts duration modeling and robust vocoder-side synthesis. Specifically, we introduce a Mixture-of-Experts Duration Predictor (MoE-DP) to capture diverse phoneme duration patterns and speaker-dependent speaking-rate characteristics. To convert richer duration variation into stable waveform generation, we further integrate a VOCOS-style vocoder with Collaborative Multi-Band and Sub-Band Discriminators. Experiments on LJSpeech, VCTK, and LibriTTS show that FNH-TTS achieves improved synthesis quality, duration-category accuracy, vocoder reconstruction quality, and inference efficiency. Further analysis shows that MoE-DP is the main source of improved duration modeling, while stronger vocoder-side components are necessary for robust synthesis under richer duration variation. |
| title | FNH-TTS: Mixture-of-Experts Duration Modeling for Robust Neural Speech Synthesis |
| topic | Audio and Speech Processing |
| url | https://arxiv.org/abs/2508.12001 |