arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.02111cs.CLcs.SDeess.AS
收藏

神经编解码器语言模型是Zero-Shot文本到语音合成器

Neural Codec Language Models are Zero-Shot Text to Speech Synthesizers

Microsoft(微软)

Chengyi Wang, Sanyuan Chen, Yu Wu, Ziqiang Zhang, Long Zhou, Shujie Liu, Zhuo Chen, Yanqing Liu, Huaming Wang, Jinyu Li, Lei He, Sheng Zhao, Furu Wei

摘要:

介绍了一种用于文本到语音合成(TTS)的语言建模方法.具体来说,我们训练神经编解码器语言模型(称为Vall-E)使用离散代码来自现成的神经音频编解码器模型,并把TTS作为一个有条件的语言建模任务,而不是在以前的工作连续信号回归。在预训练阶段,我们将TTS训练数据扩展到60 K小时的英语语音,这是现有系统的数百倍。Vall-E出现了上下文学习能力,可以用来合成高质量的个性化语音,只需3秒的注册记录一个看不见的发言者作为声学提示。实验结果表明,Vall-E在语音自然度和说话人相似度方面明显优于现有的zero-shot TTS系统。另外,我们发现Vall-E在合成时可以保留说话人的情感和声音提示的声学环境。请访问https://aka.ms/valle查看我们工作的演示。

英文摘要:

We introduce a language modeling approach for text to speech synthesis (TTS). Specifically, we train a neural codec language model (called Vall-E) using discrete codes derived from an off-the-shelf neural audio codec model, and regard TTS as a conditional language modeling task rather than continuous signal regression as in previous work. During the pre-training stage, we scale up the TTS training data to 60K hours of English speech which is hundreds of times larger than existing systems. Vall-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with only a 3-second enrolled recording of an unseen speaker as an acoustic prompt. Experiment results show that Vall-E significantly outperforms the state-of-the-art zero-shot TTS system in terms of speech naturalness and speaker similarity. In addition, we find Vall-E could preserve the speaker's emotion and acoustic environment of the acoustic prompt in synthesis. See https://aka.ms/valle for demos of our work.

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。

↑