Events

Modelling Emotions in Music: Advances in Conceptual, Contextual and Validity Issues

Tuomas Eerola

Department of Music, Durham University, UK

Modelling emotion recognition and induction by music has garnered increased attention during the last years. The present work puts together observations of the issues that need attention in order to make advances in music emotion recognition. These are divided into conceptual, contextual and data validity issues. Within each issue, the central dilemmas are discussed and promising further avenues are presented. In conceptual issues, significant discrepancies in the terminologies and choices for emotion focus and models exist. In contextual issues, the primary area of improvement is incorporating music and user contexts into emotion recognition. For the validity of data, reliable estimation of mid-level musical concepts require significant attention and optimal combination of studies with high validity and high stimulus quantity is the key to robust music emotion recognition models.
 

Bio of presenter

Tuomas Eerola is professor of music cognition at Durham University, UK. He studied music cognition combining musicology and psychology at the University of Jyväskylä, Finland. After completing MA in 1997, he took postgraduate studies at the University of Leicester, UK, and was enrolled to Graduate School of Music and Sound Research in Finland, from which he was awarded a PhD in musicology in 2003. He has been a member of Faculty at the University of Jyväskylä, first as an Assistant Professor and from 2006 onwards as Professor. His research and teaching cover a number of areas within the psychology of music. The current projects involve perception and induction of emotions in music, which he approaches by combining computational modelling with empirical experiments. He is the first author of a widely used computational toolbox for music analysis (MIDI Toolbox, 2004), has pioneered the study of acoustic and musical correlates of emotions from audio, and has published more than 60 papers and book chapters on topics including musical similarity, melodic expectations, perception of rhythm and timbre, induction and perception of emotions. He is also on the editorial board of Psychology of Music and is consulting editor for Musicae Scientiae.

AES - Audio Engineering Society