چكيده به لاتين
Abstract:
Speech disorder or stuttering is associated with a mouth locking and a sudden interruption during the normal speech by repeating, and pulling up to the sounds, syllables, words and even phrases. Sometimes, it has destructive impact in stutterer’s social relationships. Also it has factors such as isolation, depression, etc. So Control and treatment of this disorder, especially in children is one of the goals of physicians and researchers.
The human brain is responsible for all voluntary movements and involuntary; And any action or decision of that action takes place with the command of the brain. Therefore, issues related to the bridge between thought and action is attractive to researchers.
Finding the relationship between speech disorder and brain signals and consequently, finding arising from the occurrence of speech disorders occur in the brain is among cognitive sciences and today it is attractive to scientists and researchers.
This thesis explores “Detection and control of stuttering speech with the brain-nerve signal analysis”; And is defined in three phases which include: offline detection of speech disorder, online detection of speech disorder and trying to control speech disorder, using EEG signals. The results of the first phase show that with some features extracted from the brain signals we can distinguish stuttering speech from fluent speech, half a second before the stuttering in stutterers. Also features for each person is different. But unlike the results of the first phase, the second phase results indicated the ability of intelligent detection moments of stutter, with very low accuracy, using brain signals. The third phase of the project, ie intelligent online stuttering control by laryngeal muscle stimulation device, was also with low accuracy.
Keywords: speech disorder, Signal processing, Online detection, Feature extraction, intelligent control
