SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models
Abstract
In this study, we propose a simple and efficient Non-Autoregressive (NAR) text-to-speech (TTS) system based on diffusion, named SimpleSpeech. Its simpleness shows in three aspects: (1) It can be trained on the speech-only dataset, without any alignment information; (2) It directly takes plain text as input and generates speech through an NAR way; (3) It tries to model speech in a finite and compact latent space, which alleviates the modeling difficulty of diffusion. More specifically, we propose a novel speech codec model (SQ-Codec) with scalar quantization, SQ-Codec effectively maps the complex speech signal into a finite and compact latent space, named scalar latent space. Benefits from SQ-Codec, we apply a novel transformer diffusion model in the scalar latent space of SQ-Codec. We train SimpleSpeech on 4k hours of a speech-only dataset, it shows natural prosody and voice cloning ability. Compared with previous large-scale TTS models, it presents significant speech quality and generation speed improvement. Demos are released.
Cite
@article{arxiv.2406.02328,
title = {SimpleSpeech: Towards Simple and Efficient Text-to-Speech with Scalar Latent Transformer Diffusion Models},
author = {Dongchao Yang and Dingdong Wang and Haohan Guo and Xueyuan Chen and Xixin Wu and Helen Meng},
journal= {arXiv preprint arXiv:2406.02328},
year = {2024}
}
Comments
Accepted by InterSpeech 2024