Autoregressive features for a thought-to-speech converter

N. Nicolaou, J. Georgiou, M. Polycarpou

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

This paper presents our investigations towards a non-invasive custom-built thought-to-speech converter that decodes mental tasks into morse code, text and then speech. The proposed system is aimed primarily at people who have lost their ability to communicate via conventional means. The investigations presented here are part of our greater search for an appropriate set of features, classifiers and mental tasks that would maximise classification accuracy in such a system. Here Autoregressive (AR) coefficients and Power Spectral Density (PSD) features have been classified using a Support Vector Machine (SVM). The classification accuracy was higher with AR features compared to PSD. In addition, the use of an SVM to classify the AR coefficients increased the classification rate by up to 16.3% compared to that reported in different work, where other classifiers were used. It was also observed that the combination of mental tasks for which highest classification was obtained varied from subject to subject; hence the mental tasks to be used should be carefully chosen to match each subject.

Original languageEnglish
Title of host publicationBIODEVICES 2008 - Proceedings of the 1st International Conference on Biomedical Electronics and Devices
Pages11-16
Number of pages6
Volume1
Publication statusPublished - 1 Dec 2008
Externally publishedYes
EventBIODEVICES 2008 - 1st International Conference on Biomedical Electronics and Devices - Funchal, Madeira, Portugal
Duration: 28 Jan 200831 Jan 2008

Conference

ConferenceBIODEVICES 2008 - 1st International Conference on Biomedical Electronics and Devices
Country/TerritoryPortugal
CityFunchal, Madeira
Period28/01/0831/01/08

Keywords

  • Brain-computer interface
  • Electroencephalogram
  • Morse code
  • Speech impairment
  • Thought communication

Fingerprint

Dive into the research topics of 'Autoregressive features for a thought-to-speech converter'. Together they form a unique fingerprint.

Cite this