Abstract
This paper presents the results of our research in silent speech recognition (SSR) using Surface Electromyography (sEMG); which is the technology of recording the electric activation potentials of the human articulatory muscles by surface electrodes in order to recognize speech. Though SSR is still in the experimental stage, a number of potential applications seem evident. Persons who have undergone a laryngectomy, or older people for whom speaking requires a substantial effort, would be able to mouth (vocalize) words rather than actually pronouncing them. Our system has been trained with 30 utterances from each of the three subjects we had on a testing vocabulary of 4 phrases, and then tested for 15 new utterances that were not part of the training list. The system achieved an average of 91.11% word accuracy when using Support Vector Machine (SVM) classifier while the base language is English, and an average of 89.44% word accuracy using the Standard Arabic language.
Highlights
Automatic speech recognition (ASR) is a computer-based speech-to-text process, in which speech is recorded with acoustical microphones by capturing air pressure changes
WORK We have presented in this paper the results of our work for developing an isolated word Silent Speech Recognition System for both Arabic and English words
The technology is based on Surface Electromyography; which is capturing and recording of electrical potentials that arise from the muscle activity using surface electrodes attached to the skin
Summary
Automatic speech recognition (ASR) is a computer-based speech-to-text process, in which speech is recorded with acoustical microphones by capturing air pressure changes. ASR has matured to a point where it is successfully deployed in a wide variety of every-day life applications, including telephone based services and speech-driven applications on all sorts of mobile personal digital devices [1]-[2] Despite this success, speech-driven technologies still face two major challenges: first, recognition performance degrades significantly in the presence of noise. People who have undergone s laryngectomy which is surgical removal of the larynx due to cancer suffer a lot to communicate with others These facts have motivated us to investigate the possibility of developing a Silent-Speech Recognition system (SSR) which will be able to recognize phrases that describe the basic needs of a person especially if he's spending most of his time in a care/nursing home.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
