XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model
This addresses the problem of limited language support in zero-shot TTS for low/medium-resource languages, though it is incremental as it builds upon existing models.
The paper tackles the limitation of existing zero-shot multi-speaker text-to-speech models to only a few high-resource languages by proposing XTTS, a massively multilingual model trained on 16 languages, which achieved state-of-the-art results in most of them.
Most Zero-shot Multi-speaker TTS (ZS-TTS) systems support only a single language. Although models like YourTTS, VALL-E X, Mega-TTS 2, and Voicebox explored Multilingual ZS-TTS they are limited to just a few high/medium resource languages, limiting the applications of these models in most of the low/medium resource languages. In this paper, we aim to alleviate this issue by proposing and making publicly available the XTTS system. Our method builds upon the Tortoise model and adds several novel modifications to enable multilingual training, improve voice cloning, and enable faster training and inference. XTTS was trained in 16 languages and achieved state-of-the-art (SOTA) results in most of them.