# GenerTTS: Pronunciation Disentanglement for Timbre and Style Generalization in Cross-Lingual Text-to-Speech

arXiv: https://arxiv.org/abs/2306.15304 · HTML: https://mlsanity.com/paper/2306.15304/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Jun 2023.

## Built on by (most cited first, 1 of 1)

- [CrossSpeech++: Cross-lingual Speech Synthesis with Decoupled Language and Speaker Generation](https://mlsanity.com/paper/2412.20048/) (2024)

## Abstract (arXiv)

Cross-lingual timbre and style generalizable text-to-speech (TTS) aims to synthesize speech with a specific reference timbre or style that is never trained in the target language. It encounters the following challenges: 1) timbre and pronunciation are correlated since multilingual speech of a specific speaker is usually hard to obtain; 2) style and pronunciation are mixed because the speech style contains language-agnostic and language-specific parts. To address these challenges, we propose GenerTTS, which mainly includes the following works: 1) we elaborately design a HuBERT-based information bottleneck to disentangle timbre and pronunciation/style; 2) we minimize the mutual information between style and language to discard the language-specific information in the style embedding. The experiments indicate that GenerTTS outperforms baseline systems in terms of style similarity and pronunciation accuracy, and enables cross-lingual timbre and style generalization.