Please use this identifier to cite or link to this item:
Title: Dimensional Music Emotion Recognition: Combining Standard and Melodic Audio Features
Authors: Panda, Renato 
Rocha, Bruno 
Paiva, Rui Pedro 
Keywords: music emotion recognition; machine learning; regression; standard audio features; melodic features
Issue Date: 15-Oct-2013
Project: info:eu-repo/grantAgreement/FCT/5876-PPCDTI/102185/PT/MOODetector - A System for Mood-based Classification and Retrieval of Audio Music 
Serial title, monograph or event: 10th International Symposium on Computer Music Multidisciplinary Research – CMMR 2013
Place of publication or event: Marseille, France
Abstract: We propose an approach to the dimensional music emotion recognition (MER) problem, combining both standard and melodic audio features. The dataset proposed by Yang is used, which consists of 189 audio clips. From the audio data, 458 standard features and 98 melodic features were extracted. We experimented with several supervised learning and feature selection strategies to evaluate the proposed approach. Employing only standard audio features, the best attained performance was 63.2% and 35.2% for arousal and valence prediction, respectively (R2 statistics). Combining standard audio with melodic features, results improved to 67.4 and 40.6%, for arousal and valence, respectively. To the best of our knowledge, these are the best results attained so far with this dataset.
Rights: openAccess
Appears in Collections:I&D CISUC - Artigos em Livros de Actas

Show full item record

Page view(s)

checked on May 21, 2024


checked on May 21, 2024

Google ScholarTM


This item is licensed under a Creative Commons License Creative Commons