Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.21164 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917440570523648 |
|---|---|
| author | Mai, Jialong Xing, Xiaofen Xu, Xiangmin |
| author_facet | Mai, Jialong Xing, Xiaofen Xu, Xiangmin |
| contents | Fine-grained local timing control is still absent from modern text-to-speech systems: existing approaches typically provide only utterance-level duration or global speaking-rate control, while precise token-level timing manipulation remains unavailable. To the best of our knowledge, MAGIC-TTS is the first TTS model with explicit local timing control over token-level content duration and pause. MAGIC-TTS is enabled by explicit token-level duration conditioning, carefully prepared high-confidence duration supervision, and training mechanisms that correct zero-value bias and make the model robust to missing local controls. On our timing-control benchmark, MAGIC-TTS substantially improves token-level duration and pause following over spontaneous synthesis. Even when no timing control is provided, MAGIC-TTS maintains natural high-quality synthesis. We further evaluate practical local editing with a scenario-based benchmark covering navigation guidance, guided reading, and accessibility-oriented code reading. In this setting, MAGIC-TTS realizes a reproducible uniform-timing baseline and then moves the edited regions toward the requested local targets with low mean bias. These results show that explicit fine-grained controllability can be implemented effectively in a high-quality TTS system and can support realistic local timing-editing applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_21164 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MAGIC-TTS: Fine-Grained Controllable Speech Synthesis with Explicit Local Duration and Pause Control Mai, Jialong Xing, Xiaofen Xu, Xiangmin Sound Fine-grained local timing control is still absent from modern text-to-speech systems: existing approaches typically provide only utterance-level duration or global speaking-rate control, while precise token-level timing manipulation remains unavailable. To the best of our knowledge, MAGIC-TTS is the first TTS model with explicit local timing control over token-level content duration and pause. MAGIC-TTS is enabled by explicit token-level duration conditioning, carefully prepared high-confidence duration supervision, and training mechanisms that correct zero-value bias and make the model robust to missing local controls. On our timing-control benchmark, MAGIC-TTS substantially improves token-level duration and pause following over spontaneous synthesis. Even when no timing control is provided, MAGIC-TTS maintains natural high-quality synthesis. We further evaluate practical local editing with a scenario-based benchmark covering navigation guidance, guided reading, and accessibility-oriented code reading. In this setting, MAGIC-TTS realizes a reproducible uniform-timing baseline and then moves the edited regions toward the requested local targets with low mean bias. These results show that explicit fine-grained controllability can be implemented effectively in a high-quality TTS system and can support realistic local timing-editing applications. |
| title | MAGIC-TTS: Fine-Grained Controllable Speech Synthesis with Explicit Local Duration and Pause Control |
| topic | Sound |
| url | https://arxiv.org/abs/2604.21164 |