LibriTTS

Dataset Information
Modalities
Texts, Audio, Speech
Languages
English
Introduced
2019
License
Unknown
Homepage
Official Website
Contents

Overview

LibriTTS is a multi-speaker English corpus of approximately 585 hours of read English speech at 24kHz sampling rate, prepared by Heiga Zen with the assistance of Google Speech and Google Brain team members. The LibriTTS corpus is designed for TTS research. It is derived from the original materials (mp3 audio files from LibriVox and text files from Project Gutenberg) of the LibriSpeech corpus. The main differences from the LibriSpeech corpus are listed below:

  • The audio files are at 24kHz sampling rate.
  • The speech is split at sentence breaks.
  • Both original and normalized texts are included.
  • Contextual information (e.g., neighbouring sentences) can be extracted.
  • Utterances with significant background noise are excluded.

Variants: LibriTTS

Associated Benchmarks

This dataset is used in 1 benchmark:

Recent Benchmark Submissions

Task Model Paper Date
Speech Synthesis PeriodWave-Turbo-L Accelerating High-Fidelity Waveform Generation via … 2024-08-15
Speech Synthesis PeriodWave + FreeU PeriodWave: Multi-Period Flow Matching for … 2024-08-14
Speech Synthesis RFWave RFWave: Multi-band Rectified Flow for … 2024-03-08
Speech Synthesis EVA-GAN-base EVA-GAN: Enhanced Various Audio Generation … 2024-01-31
Speech Synthesis EVA-GAN-big EVA-GAN: Enhanced Various Audio Generation … 2024-01-31
Speech Synthesis BigVSAN BigVSAN: Enhancing GAN-based Neural Vocoders … 2023-09-06
Speech Synthesis BigVSAN (w/ snakebeta) BigVSAN: Enhancing GAN-based Neural Vocoders … 2023-09-06
Speech Synthesis Vocos Vocos: Closing the gap between … 2023-06-01
Speech Synthesis BigVGAN-base BigVGAN: A Universal Neural Vocoder … 2022-06-09
Speech Synthesis BigVGAN-v2 BigVGAN: A Universal Neural Vocoder … 2022-06-09
Speech Synthesis BigVGAN BigVGAN: A Universal Neural Vocoder … 2022-06-09
Speech Synthesis HiFi-GAN HiFi-GAN: Generative Adversarial Networks for … 2020-10-12
Speech Synthesis SC-WaveRNN Speaker Conditional WaveRNN: Towards Universal … 2020-08-09
Speech Synthesis WaveFlow WaveFlow: A Compact Flow-based Model … 2019-12-03
Speech Synthesis WaveGlow WaveGlow: A Flow-based Generative Network … 2018-10-31

Research Papers

Recent papers with results on this dataset:

External Links: