LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech
Abstract
This paper introduces a new speech corpus called “LibriTTS” designed for text-to-speech use. It is derived from the original audio and text materials of the LibriSpeech corpus, which has been used for training and evaluating automatic speech recognition systems. The new corpus inherits desired properties of the LibriSpeech corpus while addressing a number of issues which make LibriSpeech less than ideal for text-to-speech work. The released corpus consists of 585 hours of speech data at 24kHz sampling rate from 2,456 speakers and the corresponding texts. Experimental results show that neural end-to-end TTS models trained from the LibriTTS corpus achieved above 4.0 in mean opinion scores in naturalness in five out of six evaluation speakers. The corpus is freely available for download from http://www.openslr.org/60/.
中文速览
高质量语音合成（TTS）数据集长期依赖单说话人录音棚数据，而面向语音识别设计的大规模多说话人语料库LibriSpeech虽被TTS研究借用，却存在采样率仅16kHz、按静音而非句子切分、缺少标点大小写、无上下文信息以及含噪声样本等先天缺陷。为此，作者从LibriVox原始MP3音频和Project Gutenberg文本出发，通过句子切分、强制对齐、信噪比过滤等一整套流水线，重新构建了名为LibriTTS的语料库：包含2456位说话人、共585小时的24kHz高采样率语音，并保留了原始与规范化双版本文本及上下文句子信息。用该语料库训练的神经端到端TTS模型（GMVAE-Tacotron + WaveRNN声码器）在六位评测说话人中有五位的自然度MOS得分超过4.0分，且24kHz版本始终优于降采样至16kHz的对照组，证明更高采样率带来了可感知的质量提升。LibriTTS以宽松开源协议免费发布，为多说话人TTS、迁移学习、韵律建模等研究提供了一个更适用的大规模公开基准。
原文 arXiv:1904.02882;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1904.02882v1