Application of Malay speech technology in Malay speech therapy assistance tools

Abstract

Malay Speech Therapy Assistance Tools (MSTAT) is a system which assists the therapist to diagnose children for language disorder and to train children with stuttering problem. The main engine behind it is the speech technologies; consist of speech recognition system, Malay text-to-speech system and Malay Talking Head [1-4]. In this project, speech recognition system utilizes the Hidden Markov Model (HMM) technique for evaluating speech problem for children such as stuttering. The voice pattern of the normal and speech disorder children are used to train the HMM model for classifying the problem of speech disorder. Thus, the system is localized with local dialect voice database which focus on local Malay dialect that is currently not available in market. Besides that, the system also utilizes Malay text-to-speech system and Talking Head to guide and lead the children or parents to follow the diagnostic process. This feature makes the system more interactive and not only single direction of communication.