Popular GitHub Repositories for Avsr

Official repo for "Audio-Visual Speech Recognition In-the-Wild: Multi-Angle Vehicle Cabin Corpus and Attention-based Method" in ICASSP 2024

This repository contains the development of SynthAVSR, the first Audiovisual Speech Recognition (AVSR) system tailored for the Spanish and Catalan languages. Based on the AV-HuBERT (Audio-Visual Hidden Unit BERT) model, SynthAVSR leverages synthetic audiovisual data to bridge the gap in speech recognition technology for these languages.