Opens in a new tab

AES E-Library

← Back to search

Engineering Brief

Prediction of Valence and Arousal from Music Features

Authors: den Brinker, Albertus; van Dinther, Ralph; Skowronek, J.

AES Convention 131 · Paper 39 · October 2011

Abstract

Mood is an important attribute of music, and knowledge on mood can be used as a basic ingredient in music recommender and retrieval systems. Moods are assumed to be dominantly determined by two dimensions: valence and arousal. An experiment was conducted to attain data for song-based ratings of valence and arousal. It is shown that subject-averaged valence and arousal can be predicted from music features by a linear model.

Details

Published in
AES Convention 131
AES Convention
131
Paper number
39
Publication date
October 6, 2011
Session subject
Perception
Affiliation
Philips Research Laboratories Eindhoven; Technical University Berlin (See document for exact affiliation information.)
Type
Engineering Brief