无需训练，通过多粒度伪造检测提升语音合成质量
MSpoofTTS: Multi-Resolution Spoof-Guided Inference for Discrete Speech Synthesis
- 用多粒度检测器识别语音令牌中的异常模式
- 在解码时逐层剔除劣质候选，重排生成结果
- 不修改模型参数即可提升合成语音真实感
神经编解码语言模型实现了高质量的离散语音合成，但其推理过程仍易受令牌级伪影和分布漂移影响，导致感知真实感下降。本文提出MSpoof-TTS，一种无需训练的推理框架，通过多分辨率伪造引导实现零样本合成优化。我们设计了多分辨率令牌级伪造检测框架，在不同时间粒度下评估编解码序列，识别局部不一致或不自然的模式。随后将伪造检测器融入分层解码策略，逐步修剪低质量候选并重排假设。该判别器引导生成方式无需修改模型参数即可增强鲁棒性。实验验证了该框架在鲁棒且高质量的编解码语音生成中的有效性。音频样例与代码已公开。
原文摘要 · Abstract (English)
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 and code are available.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。