SPEECH AND LANGUAGE TECHNOLOGY GROUP AT UNIVERSITY OF MALAYA
PRINCIPLE INVESTIGATOR: DR. MUMTAZ BEGUM MUSTAFA
DEPARTMENT OF SOFTWARE ENGINEERING
FACULTY OF COMPUTER SCIENCE & INFORMATION TECHNOLOGY
UNIVERSITY OF MALAYA
1. Automatic Speech Recognition system
2. Speech-to-Speech Translation system
Speech Technology is opening a new chapter in human-computer interaction in which speech acts as both input and output during the interaction allowing for a more natural interaction. Two of the major components of speech technology are Automatic Speech recognition (ASR) and Text-to-Speech (TTS) systems. By combining these two components a truly speech-based human computer interaction is now possible. Possible applications for this technology include language learning and cross-boundary communication.
3. Automatic Sign language Recognition system
Sign Language is the usual method of communication for hearing-impaired people. Basically sign language is a way to communicate information through hand gestures and other body actions. Because sign language is not commonly known by people without hearing disabilities they generally communicate with hearing-impaired people through sign language interpreters. Recognizing and documenting sign language has only been paid attention to recently. There have been few attempts to develop recognition systems to allow deaf people to interact with the rest of society. This research aims at identifying various techniques that can be applied in recognizing sign language. The learning and recognition techniques used in previous studies to recognize sign language include neural networks and hidden Markov models (HMMs). While each technique has its own merits and demerits, combining these techniques as hybrid could potentially increase the recognition accuracy. In this research, we propose a hybrid technique to recognize sign language with higher accuracy compared to the conventional techniques.