Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.03170 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910227442434048 |
|---|---|
| author | Liang, Qifan Liu, Yuansen Wei, Ruixin Lu, Nan Zhao, Junchuan Wang, Ye |
| author_facet | Liang, Qifan Liu, Yuansen Wei, Ruixin Lu, Nan Zhao, Junchuan Wang, Ye |
| contents | While controllable Text-to-Speech (TTS) has achieved notable progress, most existing methods remain limited to inter-utterance-level control, making fine-grained intra-utterance expression challenging due to their reliance on non-public datasets or complex multi-stage training. In this paper, we propose TED-TTS, a training-free controllable framework for pretrained zero-shot TTS to enable intra-utterance emotion and duration expression. Specifically, we propose a segment-aware emotion conditioning strategy that combines causal masking with monotonic stream alignment filtering to isolate emotion conditioning and schedule mask transitions, enabling smooth intra-utterance emotion shifts while preserving global semantic coherence. Based on this, we further propose a segment-aware duration steering strategy to combine local duration embedding steering with global EOS logit modulation, allowing local duration adjustment while ensuring globally consistent termination. To eliminate the need for segment-level manual prompt engineering, we construct a 30,000-sample multi-emotion and duration-annotated text dataset to enable LLM-based automatic prompt construction. Extensive experiments demonstrate that our training-free method not only achieves state-of-the-art intra-utterance consistency in multi-emotion and duration control, but also maintains baseline-level speech quality of the underlying TTS model. Code and audio samples are available. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03170 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TED-TTS: Training-Free Intra-Utterance Emotion and Duration Control for Text-to-Speech Synthesis Liang, Qifan Liu, Yuansen Wei, Ruixin Lu, Nan Zhao, Junchuan Wang, Ye Sound While controllable Text-to-Speech (TTS) has achieved notable progress, most existing methods remain limited to inter-utterance-level control, making fine-grained intra-utterance expression challenging due to their reliance on non-public datasets or complex multi-stage training. In this paper, we propose TED-TTS, a training-free controllable framework for pretrained zero-shot TTS to enable intra-utterance emotion and duration expression. Specifically, we propose a segment-aware emotion conditioning strategy that combines causal masking with monotonic stream alignment filtering to isolate emotion conditioning and schedule mask transitions, enabling smooth intra-utterance emotion shifts while preserving global semantic coherence. Based on this, we further propose a segment-aware duration steering strategy to combine local duration embedding steering with global EOS logit modulation, allowing local duration adjustment while ensuring globally consistent termination. To eliminate the need for segment-level manual prompt engineering, we construct a 30,000-sample multi-emotion and duration-annotated text dataset to enable LLM-based automatic prompt construction. Extensive experiments demonstrate that our training-free method not only achieves state-of-the-art intra-utterance consistency in multi-emotion and duration control, but also maintains baseline-level speech quality of the underlying TTS model. Code and audio samples are available. |
| title | TED-TTS: Training-Free Intra-Utterance Emotion and Duration Control for Text-to-Speech Synthesis |
| topic | Sound |
| url | https://arxiv.org/abs/2601.03170 |