Lip Reading Sentences 3 (LRS-3)

Emerging

3papers using it

2022first seen

The 'Lip Reading Sentences 3 (LRS-3)' dataset contains video recordings of people speaking sentences, and it is used to evaluate audio-visual automatic speech recognition (AV-ASR) systems.

🔎 Find this dataset

Papers using Lip Reading Sentences 3 (LRS-3) (3)

Audio-Visual Efficient Conformer for Robust Speech Recognition2023 · 3 cites

VCSE: Time-Domain Visual-Contextual Speaker Extraction Network2022

Streaming Audio-Visual Speech Recognition with Alignment Regularization2022