MuAViC

MuAViC is an audio-visual speech recognition dataset that contains multilingual video data in 9 languages and is used to evaluate the performance of models in noisy conditions.

Papers using MuAViC (4)

mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition2025 · 1 citesMuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation2023 · 4 citesXLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception2024Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer2024