Saved in:
Bibliographic Details
Main Authors: Zhao, Junchuan, Vu, Minh Duc, Wang, Ye
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