NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
Abstract
While recent large-scale text-to-speech (TTS) models have achieved significant progress, they still fall short in speech quality, similarity, and prosody. Considering speech intricately encompasses various attributes (e.g., content, prosody, timbre, and acoustic details) that pose significant challenges for generation, a natural idea is to factorize speech into individual subspaces representing different attributes and generate them individually. Motivated by it, we propose NaturalSpeech 3, a TTS system with novel factorized diffusion models to generate natural speech in a zero-shot way. Specifically, 1) we design a neural codec with factorized vector quantization (FVQ) to disentangle speech waveform into subspaces of content, prosody, timbre, and acoustic details; 2) we propose a factorized diffusion model to generate attributes in each subspace following its corresponding prompt. With this factorization design, NaturalSpeech 3 can effectively and efficiently model intricate speech with disentangled subspaces in a divide-and-conquer way. Experiments show that NaturalSpeech 3 outperforms the state-of-the-art TTS systems on quality, similarity, prosody, and intelligibility, and achieves on-par quality with human recordings. Furthermore, we achieve better performance by scaling to 1B parameters and 200K hours of training data.
Cite
@article{arxiv.2403.03100,
title = {NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models},
author = {Zeqian Ju and Yuancheng Wang and Kai Shen and Xu Tan and Detai Xin and Dongchao Yang and Yanqing Liu and Yichong Leng and Kaitao Song and Siliang Tang and Zhizheng Wu and Tao Qin and Xiang-Yang Li and Wei Ye and Shikun Zhang and Jiang Bian and Lei He and Jinyu Li and Sheng Zhao},
journal= {arXiv preprint arXiv:2403.03100},
year = {2024}
}
Comments
Achieving human-level quality and naturalness on multi-speaker datasets (e.g., LibriSpeech) in a zero-shot way