SPEECH RECOGNITION FOR CONNECTED WORD USING CEPSTRAL AND DYNAMIC TIME WARPING ALGORITHMS

Speech Recognition or Speech Recognizer (SR) has become an important tool for people with physical disabilities when handling Home Automation (HA) appliances. This technology is expected to improve the daily life of the elderly and the disabled so that they are always in control over their lives, and continue to live independently, to learn and stay involved in social life. The goal of the research is to solve the constraints of current Malay SR that is still in its infancy stage where there is limited research in Malay words, especially for HA applications. Since, most of the previous works were confined to wired microphone; this limitation of using wireless microphone type makes it an important area of the research. Research was carried out to develop SR word model for five (5) Malay words and five (5) English words as commands to activate and deactivate home appliances.