arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.04904eess.AScs.CLcs.SD

XTTS:一个大规模多语言零样本文本到语音模型

XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Model

Edresson Casanova, Kelly Davis, Eren Gölge, Görkem Göknar, Iulian Gulea, Logan Hart, Aya Aljafari, Joshua Meyer, Reuben Morais, Samuel Olayemi, Julian Weber

AI总结:

本文提出并开源了基于 Tortoise 改进的多语言零样本 TTS 系统 XTTS,在 16 种语言上训练并在大多数语言上取得 SOTA 效果。

摘要:

大多数零样本多说话人文本到语音(ZS-TTS)系统仅支持单一语言。尽管 YourTTS、VALL-E X、Mega-TTS 2 和 Voicebox 等模型探索了多语言 ZS-TTS,但它们仅限于少数高/中等资源语言,限制了这些模型在大多数低/中等资源语言中的应用。在本文中,我们旨在通过提出并公开提供 XTTS 系统来缓解这一问题。我们的方法建立在 Tortoise 模型之上,并添加了若干新颖的修改,以实现多语言训练、改进声音克隆,并加快训练和推理速度。XTTS 在 16 种语言上进行了训练,并在其中大多数语言上取得了最先进(SOTA)的结果。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑