Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912948775026688 |
|---|---|
| author | Liu, Changsong Wang, Tianrui Ni, Ye Peng, Yizhou Chng, Eng Siong |
| author_facet | Liu, Changsong Wang, Tianrui Ni, Ye Peng, Yizhou Chng, Eng Siong |
| contents | Streaming TTS that receives streaming text is essential for interactive systems, yet this scheme faces two major challenges: unnatural prosody due to missing lookahead and long-form collapse due to unbounded context. We propose a prosodic-boundary-aware post-training strategy, adapting a pretrained LLM-based TTS model using weakly time-aligned data. Specifically, the model is adapted to learn early stopping at specified content boundaries when provided with limited future text. During inference, a sliding-window prompt carries forward previous text and speech tokens, ensuring bounded context and seamless concatenation. Evaluations show our method outperforms CosyVoice-Style interleaved baseline in both short and long-form scenarios. In long-text synthesis, especially, it achieves a 66.2% absolute reduction in word error rate (from 71.0% to 4.8%) and increases speaker and emotion similarity by 16.1% and 1.5% relatively, offering a robust solution for streaming TTS with incremental text. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_06444 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input Liu, Changsong Wang, Tianrui Ni, Ye Peng, Yizhou Chng, Eng Siong Sound Artificial Intelligence Streaming TTS that receives streaming text is essential for interactive systems, yet this scheme faces two major challenges: unnatural prosody due to missing lookahead and long-form collapse due to unbounded context. We propose a prosodic-boundary-aware post-training strategy, adapting a pretrained LLM-based TTS model using weakly time-aligned data. Specifically, the model is adapted to learn early stopping at specified content boundaries when provided with limited future text. During inference, a sliding-window prompt carries forward previous text and speech tokens, ensuring bounded context and seamless concatenation. Evaluations show our method outperforms CosyVoice-Style interleaved baseline in both short and long-form scenarios. In long-text synthesis, especially, it achieves a 66.2% absolute reduction in word error rate (from 71.0% to 4.8%) and increases speaker and emotion similarity by 16.1% and 1.5% relatively, offering a robust solution for streaming TTS with incremental text. |
| title | Prosodic Boundary-Aware Streaming Generation for LLM-Based TTS with Streaming Text Input |
| topic | Sound Artificial Intelligence |
| url | https://arxiv.org/abs/2603.06444 |