LRW

Lip Reading in the Wild

Dataset Information
Modalities
Videos, Texts, Audio
Introduced
2016
Homepage

Overview

The Lip Reading in the Wild (LRW) dataset a large-scale audio-visual database that contains 500 different words from over 1,000 speakers. Each utterance has 29 frames, whose boundary is centered around the target word. The database is divided into training, validation and test sets. The training set contains at least 800 utterances for each class while the validation and test sets contain 50 utterances.

Source: Towards Pose-invariant Lip-Reading
Image Source: https://www.robots.ox.ac.uk/~vgg/data/lip_reading/lrw1.html

Variants: LRW, Lip Reading in the Wild, Lipreading in the Wild

Associated Benchmarks

This dataset is used in 4 benchmarks:

Recent Benchmark Submissions

Task Model Paper Date
Lip to Speech Synthesis Lip2Wav Learning Individual Speaking Styles for … 2020-05-17
Lip Reading Lip2Wav Learning Individual Speaking Styles for … 2020-05-17
Talking Face Generation LipGAN Towards Automatic Face-to-Face Translation 2020-03-01

Research Papers

Recent papers with results on this dataset: