LJSpeech

The LJ Speech Dataset

Dataset Information
Modalities
Texts, Audio
Languages
English
License
Homepage

Overview

This is a public domain speech dataset consisting of 13,100 short audio clips of a single speaker reading passages from 7 non-fiction books. A transcription is provided for each clip. Clips vary in length from 1 to 10 seconds and have a total length of approximately 24 hours. The texts were published between 1884 and 1964, and are in the public domain. The audio was recorded in 2016-17 by the LibriVox project and is also in the public domain.

Source: The LJ Speech Dataset
Image Source: https://keithito.com/LJ-Speech-Dataset/
Audio Source: https://keithito.com/LJ-Speech-Dataset/

Variants: LJSpeech

Associated Benchmarks

This dataset is used in 2 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Text-To-Speech Synthesis Matcha-TTS Matcha-TTS: A fast TTS architecture … 2023-09-06
Text-To-Speech Synthesis OverFlow OverFlow: Putting flows on top … 2022-11-13
Text-To-Speech Synthesis NaturalSpeech NaturalSpeech: End-to-End Text to Speech … 2022-05-09
Text-To-Speech Synthesis FastSpeech 2 + HiFiGAN NaturalSpeech: End-to-End Text to Speech … 2022-05-09
Text-To-Speech Synthesis VITS NaturalSpeech: End-to-End Text to Speech … 2022-05-09
Text-To-Speech Synthesis FastDiff (4 steps) FastDiff: A Fast Conditional Diffusion … 2022-04-21
Text-To-Speech Synthesis FastDiff-TTS FastDiff: A Fast Conditional Diffusion … 2022-04-21
Speech Synthesis BDDM vocoder BDDM: Bilateral Denoising Diffusion Models … 2022-03-25
Speech Synthesis Neural HMM Ablation with 1 state per phone Neural HMMs are all you … 2021-08-30
Speech Synthesis Neural HMM Neural HMMs are all you … 2021-08-30
Text-To-Speech Synthesis Grad-TTS + HiFiGAN (1000 steps) Grad-TTS: A Diffusion Probabilistic Model … 2021-05-13
Speech Synthesis DiffWave LARGE DiffWave: A Versatile Diffusion Model … 2020-09-21
Text-To-Speech Synthesis FastSpeech 2 + HiFiGAN FastSpeech 2: Fast and High-Quality … 2020-06-08
Text-To-Speech Synthesis Glow-TTS + HiFiGAN Glow-TTS: A Generative Flow for … 2020-05-22
Text-To-Speech Synthesis Flowtron Flowtron: an Autoregressive Flow-based Generative … 2020-05-12
Text-To-Speech Synthesis Tacotron 2 Flowtron: an Autoregressive Flow-based Generative … 2020-05-12
Text-To-Speech Synthesis FastSpeech (Mel + WaveGlow) FastSpeech: Fast, Robust and Controllable … 2019-05-22
Text-To-Speech Synthesis Merlin FastSpeech: Fast, Robust and Controllable … 2019-05-22
Text-To-Speech Synthesis Transformer TTS (Mel + WaveGlow) Neural Speech Synthesis with Transformer … 2018-09-19

Research Papers

Recent papers with results on this dataset: