Saved in:
Bibliographic Details
Main Authors: Guo, Hao-Han, Hu, Yao, Liu, Kun, Shen, Fei-Yu, Tang, Xu, Wu, Yi-Chen, Xie, Feng-Long, Xie, Kun, Xu, Kai-Tuo
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.03283
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910908646686720
author Guo, Hao-Han
Hu, Yao
Liu, Kun
Shen, Fei-Yu
Tang, Xu
Wu, Yi-Chen
Xie, Feng-Long
Xie, Kun
Xu, Kai-Tuo
author_facet Guo, Hao-Han
Hu, Yao
Liu, Kun
Shen, Fei-Yu
Tang, Xu
Wu, Yi-Chen
Xie, Feng-Long
Xie, Kun
Xu, Kai-Tuo
contents This work proposes FireRedTTS, a foundation text-to-speech framework, to meet the growing demands for personalized and diverse generative speech applications. The framework comprises three parts: data processing, foundation system, and downstream applications. First, we comprehensively present our data processing pipeline, which transforms massive raw audio into a large-scale high-quality TTS dataset with rich annotations and a wide coverage of content, speaking style, and timbre. Then, we propose a language-model-based foundation TTS system. The speech signal is compressed into discrete semantic tokens via a semantic-aware speech tokenizer, and can be generated by a language model from the prompt text and audio. Then, a two-stage waveform generator is proposed to decode them to the high-fidelity waveform. We present two applications of this system: voice cloning for dubbing and human-like speech generation for chatbots. The experimental results demonstrate the solid in-context learning capability of FireRedTTS, which can stably synthesize high-quality speech consistent with the prompt text and audio. For dubbing, FireRedTTS can clone target voices in a zero-shot way for the UGC scenario and adapt to studio-level expressive voice characters in the PUGC scenario via few-shot fine-tuning with 1-hour recording. Moreover, FireRedTTS achieves controllable human-like speech generation in a casual style with paralinguistic behaviors and emotions via instruction tuning, to better serve spoken chatbots.
format Preprint
id arxiv_https___arxiv_org_abs_2409_03283
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications
Guo, Hao-Han
Hu, Yao
Liu, Kun
Shen, Fei-Yu
Tang, Xu
Wu, Yi-Chen
Xie, Feng-Long
Xie, Kun
Xu, Kai-Tuo
Sound
Audio and Speech Processing
This work proposes FireRedTTS, a foundation text-to-speech framework, to meet the growing demands for personalized and diverse generative speech applications. The framework comprises three parts: data processing, foundation system, and downstream applications. First, we comprehensively present our data processing pipeline, which transforms massive raw audio into a large-scale high-quality TTS dataset with rich annotations and a wide coverage of content, speaking style, and timbre. Then, we propose a language-model-based foundation TTS system. The speech signal is compressed into discrete semantic tokens via a semantic-aware speech tokenizer, and can be generated by a language model from the prompt text and audio. Then, a two-stage waveform generator is proposed to decode them to the high-fidelity waveform. We present two applications of this system: voice cloning for dubbing and human-like speech generation for chatbots. The experimental results demonstrate the solid in-context learning capability of FireRedTTS, which can stably synthesize high-quality speech consistent with the prompt text and audio. For dubbing, FireRedTTS can clone target voices in a zero-shot way for the UGC scenario and adapt to studio-level expressive voice characters in the PUGC scenario via few-shot fine-tuning with 1-hour recording. Moreover, FireRedTTS achieves controllable human-like speech generation in a casual style with paralinguistic behaviors and emotions via instruction tuning, to better serve spoken chatbots.
title FireRedTTS: A Foundation Text-To-Speech Framework for Industry-Level Generative Speech Applications
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2409.03283