Abstract:
Researches indicate that electroencephalography (EEG) can be used to classify data of imagined speech. It can be further utilized to develop speech prosthesis and synthetic telepathy systems. The objective is to show a comparison between the Emotive Dataset processing and an algorithm for the classification performance in imagined speech by selecting the features that extract maximum discriminatory information from the data. After acquiring an offline dataset certain features were extracted. The features extracted are variance, entropy and signal energy, mean, median, standard deviation, wentropy. Afteracquiring results we applied the same algorithm to the raw EEG acquired using EmotivePRO.EEG datawas acquired from a healthy subjects who had imagined speaking vowel sounds /a/,1e/,1i/,1o/ and /u/ with 10 trials for each subject was processed to extract features. Classification was done using NV classifier. The classification accuracies obtained in this work ranges from 75-90%. The results can be used to develop better speech prosthesis or a telepathy system where most of the information from imagined speech can be extracted. By the implementation of this project a mute person will be able to communicate his word. An accidently mute person sometimes feels helpless because he have to struggle to communicate his problems to others like ifhe wants water So after training the device on a person he will then can easily communicate.
