On Distant Speech Recognition for Home Automation

摘要: In the framework of Ambient Assisted Living, home automation may be a solution for helping elderly people living alone at home. This study is part Sweet-Home project which aims developing new system based on voice command to improve support and well-being in loss autonomy. The goal vocal order recognition with focus two aspects: distance speech sentence spotting. Several ASR techniques were evaluated realistic corpus acquired 4-room flat equipped microphones set ceiling. distant French was recorded 21 speakers who acted scenarios activities daily living. Techniques acting decoding stage, such as our novel approach called Driven Decoding Algorithm (DDA), gave better results than baseline other approaches. uses best SNR channels priori knowledge (voice commands distress sentences) has demonstrated an increase rate without introducing false alarms. Generally speaking, short overview allows then outline research challenges that technologies must take up Living Augmentative Alternative Communication, current reseach avenues this domain.