LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech

TL;DR

LibriTTS is a new speech corpus derived from LibriSpeech, optimized for text-to-speech applications, containing 585 hours of speech from 2,456 speakers, enabling improved TTS model training and evaluation.

Contribution

The paper introduces LibriTTS, a large-scale, high-quality speech corpus specifically designed for TTS, addressing limitations of LibriSpeech for this purpose.

Findings

Neural end-to-end TTS models trained on LibriTTS achieved over 4.0 MOS in naturalness.

The corpus covers 585 hours of speech from 2,456 speakers.

LibriTTS is freely available for research use.

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/.