LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech
This provides a high-quality, freely available dataset for TTS research, addressing a domain-specific need for improved speech synthesis resources.
The paper introduces LibriTTS, a new speech corpus derived from LibriSpeech for text-to-speech (TTS) applications, addressing issues in the original corpus. Experimental results show that neural end-to-end TTS models trained on LibriTTS achieved mean opinion scores above 4.0 in naturalness for five out of six evaluation speakers.
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/.