FLY-TTS: Fast, Lightweight and High-Quality End-to-End Text-to-Speech Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Guo, Yinlin, Lv, Yening, Dou, Jinqiao, Zhang, Yan, Wang, Yuehai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929404531179520
author Guo, Yinlin
Lv, Yening
Dou, Jinqiao
Zhang, Yan
Wang, Yuehai
author_facet Guo, Yinlin
Lv, Yening
Dou, Jinqiao
Zhang, Yan
Wang, Yuehai
contents While recent advances in Text-To-Speech synthesis have yielded remarkable improvements in generating high-quality speech, research on lightweight and fast models is limited. This paper introduces FLY-TTS, a new fast, lightweight and high-quality speech synthesis system based on VITS. Specifically, 1) We replace the decoder with ConvNeXt blocks that generate Fourier spectral coefficients followed by the inverse short-time Fourier transform to synthesize waveforms; 2) To compress the model size, we introduce the grouped parameter-sharing mechanism to the text encoder and flow-based model; 3) We further employ the large pre-trained WavLM model for adversarial training to improve synthesis quality. Experimental results show that our model achieves a real-time factor of 0.0139 on an Intel Core i9 CPU, 8.8x faster than the baseline (0.1221), with a 1.6x parameter compression. Objective and subjective evaluations indicate that FLY-TTS exhibits comparable speech quality to the strong baseline.
format Preprint
id arxiv_https___arxiv_org_abs_2407_00753
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FLY-TTS: Fast, Lightweight and High-Quality End-to-End Text-to-Speech Synthesis
Guo, Yinlin
Lv, Yening
Dou, Jinqiao
Zhang, Yan
Wang, Yuehai
Audio and Speech Processing
Sound
While recent advances in Text-To-Speech synthesis have yielded remarkable improvements in generating high-quality speech, research on lightweight and fast models is limited. This paper introduces FLY-TTS, a new fast, lightweight and high-quality speech synthesis system based on VITS. Specifically, 1) We replace the decoder with ConvNeXt blocks that generate Fourier spectral coefficients followed by the inverse short-time Fourier transform to synthesize waveforms; 2) To compress the model size, we introduce the grouped parameter-sharing mechanism to the text encoder and flow-based model; 3) We further employ the large pre-trained WavLM model for adversarial training to improve synthesis quality. Experimental results show that our model achieves a real-time factor of 0.0139 on an Intel Core i9 CPU, 8.8x faster than the baseline (0.1221), with a 1.6x parameter compression. Objective and subjective evaluations indicate that FLY-TTS exhibits comparable speech quality to the strong baseline.
title FLY-TTS: Fast, Lightweight and High-Quality End-to-End Text-to-Speech Synthesis
topic Audio and Speech Processing
Sound
url https://arxiv.org/abs/2407.00753