NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models

TL;DR

NaturalSpeech 3 introduces a factorized diffusion-based TTS system that disentangles speech attributes into subspaces, enabling high-quality, zero-shot speech synthesis that surpasses current state-of-the-art models in multiple aspects.

Contribution

It proposes a novel factorized diffusion model with a neural codec using FVQ to disentangle speech into subspaces, improving zero-shot speech synthesis quality and flexibility.

Findings

Outperforms state-of-the-art TTS systems in quality, similarity, and prosody.

Achieves on-par quality with human recordings.

Scaling to 1B parameters and 200K hours of data further improves performance.

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.