Voice command recognition using EEG signals

These days the interfaces for working with computers have begun to grow at large. One of most actual modalities is Brain-Computer Interface (BCI). BCI is very perspective future way of communication with computers. Information speed of human speech or typewriting is relatively small. BCI's information speed may be much faster than traditional modalities. In this thesis, automatic speech recognition of spoken words from brain waves based on digital signal processing and machine learning methods is proposed. For this system, EEG database for training and testing consist of 20 volunteers was built. Recognition accuracy of 50 phrases (Robot commands) achieved accuracy up to 5%. The main motivation was to bring better understanding of speech production. Speech recognition from brain signals can to improve voice control or it can help people with disturbing speech disorders.