A fuzzy inference-based music emotion recognition system

Sanghoon Jun, Seungmin Rho, Byeong J. Han, Een Jun Hwang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

15 Citations (Scopus)

Abstract

Music is a language of emotions, and hence music emotion could be useful in music understanding, recommendation, retrieval and some other music-related applications. Many issues for music emotion recognition have been addressed by different disciplines such as physiology, psychology, cognitive science and musicology. In this paper, we focus on the challenging issue of recognizing music emotions based on subjective human emotions and acoustic music signal features and present an intelligent music emotion recognition system. In our system, music emotion recognition consists of three steps: (i) Various music features are extracted from music signal, (ii) Those music features are analyzed and mapped into some Arousal and Valence values (AV values) by a fuzzy inference engine, (iii) Music emotion is decided based on the AV values. For the accurate music emotion recognition, we invented a new user feedback method, which can minimize the emotion difference between the inference engine and user feedback. We implemented a prototype music emotion recognition system and carried out various experiments to evaluate its performance. We report some of the results.

Original languageEnglish
Title of host publicationIET Conference Publications
Pages673-677
Number of pages5
Edition543 CP
DOIs
Publication statusPublished - 2008 Dec 1
Event5th International Conference on Visual Information Engineering, VIE 2008 - Xi'an, China
Duration: 2008 Jul 292008 Aug 1

Other

Other5th International Conference on Visual Information Engineering, VIE 2008
CountryChina
CityXi'an
Period08/7/2908/8/1

Fingerprint

Inference engines
Fuzzy inference
Feedback
Physiology
Acoustics
Experiments

Keywords

  • Arousal and valence
  • Emotion recognition
  • Fuzzy logic
  • Music emotion

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Jun, S., Rho, S., Han, B. J., & Hwang, E. J. (2008). A fuzzy inference-based music emotion recognition system. In IET Conference Publications (543 CP ed., pp. 673-677) https://doi.org/10.1049/cp:20080398

A fuzzy inference-based music emotion recognition system. / Jun, Sanghoon; Rho, Seungmin; Han, Byeong J.; Hwang, Een Jun.

IET Conference Publications. 543 CP. ed. 2008. p. 673-677.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Jun, S, Rho, S, Han, BJ & Hwang, EJ 2008, A fuzzy inference-based music emotion recognition system. in IET Conference Publications. 543 CP edn, pp. 673-677, 5th International Conference on Visual Information Engineering, VIE 2008, Xi'an, China, 08/7/29. https://doi.org/10.1049/cp:20080398
Jun S, Rho S, Han BJ, Hwang EJ. A fuzzy inference-based music emotion recognition system. In IET Conference Publications. 543 CP ed. 2008. p. 673-677 https://doi.org/10.1049/cp:20080398
Jun, Sanghoon ; Rho, Seungmin ; Han, Byeong J. ; Hwang, Een Jun. / A fuzzy inference-based music emotion recognition system. IET Conference Publications. 543 CP. ed. 2008. pp. 673-677
@inproceedings{243a8b5ae59d4d72b89d736dc1454fb1,
title = "A fuzzy inference-based music emotion recognition system",
abstract = "Music is a language of emotions, and hence music emotion could be useful in music understanding, recommendation, retrieval and some other music-related applications. Many issues for music emotion recognition have been addressed by different disciplines such as physiology, psychology, cognitive science and musicology. In this paper, we focus on the challenging issue of recognizing music emotions based on subjective human emotions and acoustic music signal features and present an intelligent music emotion recognition system. In our system, music emotion recognition consists of three steps: (i) Various music features are extracted from music signal, (ii) Those music features are analyzed and mapped into some Arousal and Valence values (AV values) by a fuzzy inference engine, (iii) Music emotion is decided based on the AV values. For the accurate music emotion recognition, we invented a new user feedback method, which can minimize the emotion difference between the inference engine and user feedback. We implemented a prototype music emotion recognition system and carried out various experiments to evaluate its performance. We report some of the results.",
keywords = "Arousal and valence, Emotion recognition, Fuzzy logic, Music emotion",
author = "Sanghoon Jun and Seungmin Rho and Han, {Byeong J.} and Hwang, {Een Jun}",
year = "2008",
month = "12",
day = "1",
doi = "10.1049/cp:20080398",
language = "English",
isbn = "9780863419140",
pages = "673--677",
booktitle = "IET Conference Publications",
edition = "543 CP",

}

TY - GEN

T1 - A fuzzy inference-based music emotion recognition system

AU - Jun, Sanghoon

AU - Rho, Seungmin

AU - Han, Byeong J.

AU - Hwang, Een Jun

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Music is a language of emotions, and hence music emotion could be useful in music understanding, recommendation, retrieval and some other music-related applications. Many issues for music emotion recognition have been addressed by different disciplines such as physiology, psychology, cognitive science and musicology. In this paper, we focus on the challenging issue of recognizing music emotions based on subjective human emotions and acoustic music signal features and present an intelligent music emotion recognition system. In our system, music emotion recognition consists of three steps: (i) Various music features are extracted from music signal, (ii) Those music features are analyzed and mapped into some Arousal and Valence values (AV values) by a fuzzy inference engine, (iii) Music emotion is decided based on the AV values. For the accurate music emotion recognition, we invented a new user feedback method, which can minimize the emotion difference between the inference engine and user feedback. We implemented a prototype music emotion recognition system and carried out various experiments to evaluate its performance. We report some of the results.

AB - Music is a language of emotions, and hence music emotion could be useful in music understanding, recommendation, retrieval and some other music-related applications. Many issues for music emotion recognition have been addressed by different disciplines such as physiology, psychology, cognitive science and musicology. In this paper, we focus on the challenging issue of recognizing music emotions based on subjective human emotions and acoustic music signal features and present an intelligent music emotion recognition system. In our system, music emotion recognition consists of three steps: (i) Various music features are extracted from music signal, (ii) Those music features are analyzed and mapped into some Arousal and Valence values (AV values) by a fuzzy inference engine, (iii) Music emotion is decided based on the AV values. For the accurate music emotion recognition, we invented a new user feedback method, which can minimize the emotion difference between the inference engine and user feedback. We implemented a prototype music emotion recognition system and carried out various experiments to evaluate its performance. We report some of the results.

KW - Arousal and valence

KW - Emotion recognition

KW - Fuzzy logic

KW - Music emotion

UR - http://www.scopus.com/inward/record.url?scp=67649148218&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67649148218&partnerID=8YFLogxK

U2 - 10.1049/cp:20080398

DO - 10.1049/cp:20080398

M3 - Conference contribution

AN - SCOPUS:67649148218

SN - 9780863419140

SP - 673

EP - 677

BT - IET Conference Publications

ER -