Audio-Visual Speech Recognition using Red Exclusion and Neural Networks.

摘要: Automatic speech recognition (ASR) performs well under restricted conditions, but performance degrades in noisy environments. Audio-Visual Speech Recognition (AVSR) combats this by incorporating a visual signal into the recognition. This paper briefly reviews contribution of psycholinguistics to endeavour and recent advances machine AVSR. An important first step AVSR is that feature extraction from mouth region technique developed authors breifly presented. examines examine how useful combination with several integration arhitectures at given task, demonstrates vision does infact assist when used linguistically guided fashion, gives insight remaining issues.