1 results listed
The field of human computer interaction (HCI) involves the creation of interactive computing systems for humans to enhance the quality of life of people especially with disabilities all over the world. This study proposes a multimodal system to give the opportunity to carry out all daily works with a personal computer (PC) for disabled people that cannot use their hands. In this study, it's aimed to create an interaction between the user and a machine that is performed by user's voice and eye movements. Turkish Speech Recognition was performed by using mel-frequency cepstral coefficient (MFCC) extraction, hidden markov model (HMM) and artificial neural networks (ANN). As a joint part of the software, an efficient eye tracking system with a Tobii 4C eye tracker, was developed having a feature of eye blink detection for controlling an interface that provides an alternate way of communication. This multimodal system was developed by the authors using Java language and Matlab library and the system performed promising results for Turkish training words. To increase the system's performance, usage of natural language processing methods is planned as a future work.
International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES
Hilal Kaya
F.F. İÇEL
F. ÖZATAK
S. KARAKOÇ
O. SARIYER