loading
Documents

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Luka Kraljević ; Mladen Russo ; Mia Mlikota and Matko Šarić

Affiliation: University of Split, FESB and Laboratory for Smart Environment Technologies, Croatia

ISBN: 978-989-758-260-8

ISSN: 2184-2825

Keyword(s): Music, Emotion Detection, Cochlea, Gammatone Filterbank.

Related Ontology Subjects/Areas/Topics: Human-Machine Interface ; Multimedia ; Multimedia Signal Processing ; Multimedia Systems and Applications ; Perceptual/Human Audiovisual System Modeling ; Telecommunications

Abstract: Listening to music often evokes strong emotions. With the rapid growth of easily-accessible digital music libraries there is an increasing need in reliable music emotion recognition systems. Common musical features like tempo, mode, pitch, clarity, etc. which can be easily calculated from audio signal are associated with particular emotions and are often used in emotion detection systems. Based on the idea that humans don’t detect emotions from pure audio signal but from a signal that had been previously processed by the cochlea, in this work we propose new cochlear based features for music emotion recognition. Features are calculated from the gammatone filterbank model output and emotion classification is then performed using Support Vector Machine (SVM) and TreeBagger classifiers. Proposed features are evaluated on publicly available 1000 songs database and compared to other commonly used features. Results show that our approach is effective and outperforms other commonly used featu res. In the combined features set we achieved accuracy of 83.88% and 75.12% for arousal and valence. (More)

PDF ImageFull Text

Download
CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.94.21.209

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Kraljević, L.; Russo, M.; Mlikota, M. and Šarić, M. (2017). Cochlea-based Features for Music Emotion Classification.In Proceedings of the 14th International Joint Conference on e-Business and Telecommunications - Volume 6: SIGMAP, (ICETE 2017) ISBN 978-989-758-260-8, ISSN 2184-2825, pages 64-68. DOI: 10.5220/0006466900640068

@conference{sigmap17,
author={Luka Kraljević. and Mladen Russo. and Mia Mlikota. and Matko Šarić.},
title={Cochlea-based Features for Music Emotion Classification},
booktitle={Proceedings of the 14th International Joint Conference on e-Business and Telecommunications - Volume 6: SIGMAP, (ICETE 2017)},
year={2017},
pages={64-68},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006466900640068},
isbn={978-989-758-260-8},
}

TY - CONF

JO - Proceedings of the 14th International Joint Conference on e-Business and Telecommunications - Volume 6: SIGMAP, (ICETE 2017)
TI - Cochlea-based Features for Music Emotion Classification
SN - 978-989-758-260-8
AU - Kraljević, L.
AU - Russo, M.
AU - Mlikota, M.
AU - Šarić, M.
PY - 2017
SP - 64
EP - 68
DO - 10.5220/0006466900640068

Login or register to post comments.

Comments on this Paper: Be the first to review this paper.