Jessica Esteve Pitarch

MSc Diploma Project

Title

Playing music using EEG signals

Candidate

Jessica Esteve Pitarch

Supervisor

Prof. Dr. Touradj Ebrahimi

Assistant: Ashkan Yazdani

Expected

October 22,  2010

Place

EPFL

Description

Sonification is the use of non-speech audio to convey information or perceptualize data. Due to the specifics of auditory perception, such as temporal and pressure resolution, it forms an interesting alternative to visualization techniques, gaining importance in various disciplines. Electroencephalogram (EEG) signal is a biological signal which can reflect the changes in electrical activity of the human brain during different mental tasks. EEG sonification will let us investigate this signal by hearing it and therefore we can analyze the changes in the sonified EEG during different mental tasks. Several attempts have been made for EEG sonification which have led to promising results.
In this project, we are interested in analysis of the EEG signal and playing music by means of this signal. To this end, time frequency signal decomposition techniques will be used to map the EEG signals onto musical scores. Finally, the result of this offline analysis will be used to produce music online. The following tasks should be performed:
 

  1. Review the state of the art in music theory and EEG signal processing.
  2. Study different methods for time frequency analysis of the EEG signal.
  3. Study the state of the art in time and frequency localization of “bumps” in decomposed signals.
  4. Studying different methods of mapping signal bumps into music scores.
  5. Exploring various methods to create, modify, and process MIDI files with Matlab.
  6. Implement and validate a tool to generate music offline, using EEG signals. A GUI will be developed which includes following options:
    1. Selection of the signal and electrodes.
    2. Selection of the methods to decompose the signal and detect bumps.
    3. Possibly displaying the musical scores.
  7. Implement and validate a tool to generate music offline, using EEG signals and testing it on several subjects.
  8. Assessment and comparison of different methods used for signal processing and music generation.
  9. Create an on-line demonstrator.