Phrase-Localized Language-Contrastive Guidance: Training-Free Localized Accent Control for Code-Switching Text-to-Speech

2026-09-01

AI Summary

为解决语音合成中代码切换导致的非本地口音问题，提出了一种无需训练的推理框架LCG，通过自注意力探查技术定位短语边界，并对各区域应用独立的语言引导。

Abstract

Current speech synthesis struggles with code-switching, which mixes a foreign language phrase into a primary language utterance, causing the phrase to be spoken with the primary language's accent rather than its native one. We propose Phrase-Localized Language-Contrastive Guidance (LCG), a training-free inference framework that restores a native accent to code-switched phrases in cross-lingual text-to-speech. LCG replaces the single language guidance applied across the whole utterance with a separate guidance for each region, so each part is guided by its own language. To choose where to apply this localized guidance, we propose a self-attention probing technique that finds the phrase boundaries without external alignments. Together, these components generate speech in which each region carries the accent of its own language, requiring no fine-tuning or auxiliary models. Across diverse language pairs, LCG robustly increases the nativeness of the code-switched phrase while suppressing accent leakage, and preserving overall speaker identity and naturalness.

Problem

• code-switching
• accent control
• text-to-speech

Innovation

• Phrase-Localized Language-Contrastive Guidance
• training-free inference framework
• self-attention probing technique
• accent restoration