Vowel Classification from Imagined Speech Using Machine Learning
Name
Markus-Oliver Tamm
Abstract
Imagined speech is a relatively new EEG neuro-paradigm, which has seen little use in BCI applications. Imagined speech can be used to allow physically impaired patients to communicate and to use smart devices by imagining desired commands and then detect-ing and executing those commands in a smart device.
The goal of this research is to verify previous classification attempts made and then de-sign a new, more efficient neural network that is noticeably less complex (fewer number of layers) that still achieves a comparable classification accuracy. The classifiers are de-signed to distinguish between EEG signal patterns corresponding to imagined speech of different vowels and words. This research uses a dataset that consists of 15 subjects imag-ining saying the 5 main vowels (a, e, i, o, u) and 6 different words 2 previous researches on imagined speech classification done on this same dataset are replicated and the repli-cation results are compared. The pre-processing of data is described and a new CNN clas-sifier with 3 different Transfer Learning methods are described and used to classify EEG signals. Classification accuracy is used as the performance metric.
The goal of this research is to verify previous classification attempts made and then de-sign a new, more efficient neural network that is noticeably less complex (fewer number of layers) that still achieves a comparable classification accuracy. The classifiers are de-signed to distinguish between EEG signal patterns corresponding to imagined speech of different vowels and words. This research uses a dataset that consists of 15 subjects imag-ining saying the 5 main vowels (a, e, i, o, u) and 6 different words 2 previous researches on imagined speech classification done on this same dataset are replicated and the repli-cation results are compared. The pre-processing of data is described and a new CNN clas-sifier with 3 different Transfer Learning methods are described and used to classify EEG signals. Classification accuracy is used as the performance metric.
Graduation Thesis language
English
Graduation Thesis type
Bachelor - Computer Science
Supervisor(s)
Yar Muhammad, Naveed Muhammad
Defence year
2020