Alternative speech communication based on Cued Speech

This study focuses on alternative speech communication based on Cued Speech. Cued Speech is a visual mode of communication that uses handshapes and placements in combination with the mouth movements of speech to make the phonemes of a spoken language look different from each other and clearly understandable to deaf and hearing-impaired people. Originally, the aim of Cued Speech was to overcome the problems of lip reading and thus enable deaf children and adults to wholly understand spoken language. In this study, we investigate the use of Cued Speech not only for perception, but also for speech production in the case of speech- or hearing-impaired individuals. The proposed method is based on hidden Markov model (HMM) automatic recognition. Automatic recognition of Cued Speech can be served as an alternative speech communication method for individuals with speech- or hearing impairments. This article presents vowel and consonant, and also isolated word recognition experiments for Cued Speech for French. The results obtained are promising and comparable to the results obtained when using audio signal.