Audio-Visual Speech Recognition using Sequence to Sequence Models

GitHub page


Sigmedia-AVSR is an open-source research system for Speech Recognition, developed by the Sigmedia team in Trinity College Dublin, Ireland.

Written entirely in Python, Sigmedia-AVSR aims to provide a simple and reproducible way of training and evaluating speech recognition models based on sequence to sequence neural networks. Sigmedia-AVSR can exploit both auditory and visual speech modalities, considered either independently (ASR, VSR) or together (AVSR).

Page last modified on September 10, 2018