Training a Classifier to Detect Instantaneous Musical Cognitive States

TitleTraining a Classifier to Detect Instantaneous Musical Cognitive States
Publication TypeConference Paper
Year of Publication2006
Conference NameInternational Conference on Music Perception and Cognition
AuthorsRamirez, R., & Puiggròs M.
AbstractThe study of human brain functions has dramatically increased in recent years greatly due to the advent of Functional Magnetic Resonance Imaging (fMRI). While fMRI has been extensively used to test hypothesis regarding the location of activation for different brain functions, the problem of automatically decoding cognitive states has been little explored. The study of this problem is important because it can provide a tool for detecting cognitive processes useful for diagnosing difficulties in performing a task. In this paper we detect, in a musical context, the instantaneous cognitive state of a person based on her Functional Magnetic Resonance Imaging data. We describe a machine learning approach to the problem of discriminating a cognitive state produced by listening to melodic tonal stimuli from (1) a cognitive state produced by listening to speech stimuli, and (2) a cognitive state produced by mentally rehearsing a tonal melody.
intranet