Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.05373 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911583577309184 |
|---|---|
| author | Zhao, Junchuan Vu, Minh Duc Wang, Ye |
| author_facet | Zhao, Junchuan Vu, Minh Duc Wang, Ye |
| contents | Neural codec language models enable high-quality discrete speech synthesis, yet their inference remains vulnerable to token-level artifacts and distributional drift that degrade perceptual realism. Rather than relying on preference optimization or retraining, we propose MSpoof-TTS, a training-free inference framework that improves zero-shot synthesis through multi-resolution spoof guidance. We introduce a Multi-Resolution Token-based Spoof Detection framework that evaluates codec sequences at different temporal granularities to detect locally inconsistent or unnatural patterns. We then integrate the spoof detectors into a hierarchical decoding strategy, progressively pruning low-quality candidates and re-ranking hypotheses. This discriminator-guided generation enhances robustness without modifying model parameters. Experiments validate the effectiveness of our framework for robust and high-quality codec-based speech generation. Audio samples are available at https://danny-nus.github.io/MSpoofTTS.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05373 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Hierarchical Decoding for Discrete Speech Synthesis with Multi-Resolution Spoof Detection Zhao, Junchuan Vu, Minh Duc Wang, Ye Sound Audio and Speech Processing Neural codec language models enable high-quality discrete speech synthesis, yet their inference remains vulnerable to token-level artifacts and distributional drift that degrade perceptual realism. Rather than relying on preference optimization or retraining, we propose MSpoof-TTS, a training-free inference framework that improves zero-shot synthesis through multi-resolution spoof guidance. We introduce a Multi-Resolution Token-based Spoof Detection framework that evaluates codec sequences at different temporal granularities to detect locally inconsistent or unnatural patterns. We then integrate the spoof detectors into a hierarchical decoding strategy, progressively pruning low-quality candidates and re-ranking hypotheses. This discriminator-guided generation enhances robustness without modifying model parameters. Experiments validate the effectiveness of our framework for robust and high-quality codec-based speech generation. Audio samples are available at https://danny-nus.github.io/MSpoofTTS.github.io/. |
| title | Hierarchical Decoding for Discrete Speech Synthesis with Multi-Resolution Spoof Detection |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2603.05373 |