Hidden Markov models merging acoustic and articulatory information to automatic speech recognition

This paper describes a new scheme for robust speech recognition systems where visual information and acoustic features are merged. Using the "pseudo-diphone" as the robust unit, we compare a global hidden Markov model (HMM) and a master/slave HMM through a centisecond preprocessing and through a segmental one. We confirm by experimentation the importance of articulatory features in clean and noisy environments.