Investigation of the relationships between audio features and induced emotions in Contemporary Western music

Konstantinos Trochidis, Charles Delbé, Emmanuel Bigand

Research output: Contribution to conferencePaper

Abstract

This paper focuses on emotion recognition and understanding in Contemporary Western music. The study seeks to investigate the relationship between perceived emotion and musical features in the fore-mentioned musical genre. A set of 27 Contemporary music excerpts is used as stimuli to gather responses from both musicians and non-musicians which are then mapped on an emotional plane in terms of arousal and valence dimensions. Audio signal analysis techniques are applied to the corpus and a base feature set is obtained. The feature set contains characteristics ranging from low-level spectral and temporal acoustic features to high-level contextual features. The feature extraction process is discussed with particular emphasis on the interaction between acoustical and structural parameters. Statistical relations between audio features and emotional ratings from psychological experiments are systematically investigated. Finally, a linear model is created using the best features and the mean ratings and its prediction efficiency is evaluated and discussed.

Original languageEnglish (US)
StatePublished - Jan 1 2011
Event8th Sound and Music Computing Conference, SMC 2011 - Padova, Italy
Duration: Jul 6 2011Jul 9 2011

Other

Other8th Sound and Music Computing Conference, SMC 2011
CountryItaly
CityPadova
Period7/6/117/9/11

Fingerprint

Signal analysis
Feature extraction
Acoustics
Experiments

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Trochidis, K., Delbé, C., & Bigand, E. (2011). Investigation of the relationships between audio features and induced emotions in Contemporary Western music. Paper presented at 8th Sound and Music Computing Conference, SMC 2011, Padova, Italy.

Investigation of the relationships between audio features and induced emotions in Contemporary Western music. / Trochidis, Konstantinos; Delbé, Charles; Bigand, Emmanuel.

2011. Paper presented at 8th Sound and Music Computing Conference, SMC 2011, Padova, Italy.

Research output: Contribution to conferencePaper

Trochidis, K, Delbé, C & Bigand, E 2011, 'Investigation of the relationships between audio features and induced emotions in Contemporary Western music', Paper presented at 8th Sound and Music Computing Conference, SMC 2011, Padova, Italy, 7/6/11 - 7/9/11.
Trochidis K, Delbé C, Bigand E. Investigation of the relationships between audio features and induced emotions in Contemporary Western music. 2011. Paper presented at 8th Sound and Music Computing Conference, SMC 2011, Padova, Italy.
Trochidis, Konstantinos ; Delbé, Charles ; Bigand, Emmanuel. / Investigation of the relationships between audio features and induced emotions in Contemporary Western music. Paper presented at 8th Sound and Music Computing Conference, SMC 2011, Padova, Italy.
@conference{9a7a41f8bb1f4929bdcebb5d6b935d57,
title = "Investigation of the relationships between audio features and induced emotions in Contemporary Western music",
abstract = "This paper focuses on emotion recognition and understanding in Contemporary Western music. The study seeks to investigate the relationship between perceived emotion and musical features in the fore-mentioned musical genre. A set of 27 Contemporary music excerpts is used as stimuli to gather responses from both musicians and non-musicians which are then mapped on an emotional plane in terms of arousal and valence dimensions. Audio signal analysis techniques are applied to the corpus and a base feature set is obtained. The feature set contains characteristics ranging from low-level spectral and temporal acoustic features to high-level contextual features. The feature extraction process is discussed with particular emphasis on the interaction between acoustical and structural parameters. Statistical relations between audio features and emotional ratings from psychological experiments are systematically investigated. Finally, a linear model is created using the best features and the mean ratings and its prediction efficiency is evaluated and discussed.",
author = "Konstantinos Trochidis and Charles Delb{\'e} and Emmanuel Bigand",
year = "2011",
month = "1",
day = "1",
language = "English (US)",
note = "8th Sound and Music Computing Conference, SMC 2011 ; Conference date: 06-07-2011 Through 09-07-2011",

}

TY - CONF

T1 - Investigation of the relationships between audio features and induced emotions in Contemporary Western music

AU - Trochidis, Konstantinos

AU - Delbé, Charles

AU - Bigand, Emmanuel

PY - 2011/1/1

Y1 - 2011/1/1

N2 - This paper focuses on emotion recognition and understanding in Contemporary Western music. The study seeks to investigate the relationship between perceived emotion and musical features in the fore-mentioned musical genre. A set of 27 Contemporary music excerpts is used as stimuli to gather responses from both musicians and non-musicians which are then mapped on an emotional plane in terms of arousal and valence dimensions. Audio signal analysis techniques are applied to the corpus and a base feature set is obtained. The feature set contains characteristics ranging from low-level spectral and temporal acoustic features to high-level contextual features. The feature extraction process is discussed with particular emphasis on the interaction between acoustical and structural parameters. Statistical relations between audio features and emotional ratings from psychological experiments are systematically investigated. Finally, a linear model is created using the best features and the mean ratings and its prediction efficiency is evaluated and discussed.

AB - This paper focuses on emotion recognition and understanding in Contemporary Western music. The study seeks to investigate the relationship between perceived emotion and musical features in the fore-mentioned musical genre. A set of 27 Contemporary music excerpts is used as stimuli to gather responses from both musicians and non-musicians which are then mapped on an emotional plane in terms of arousal and valence dimensions. Audio signal analysis techniques are applied to the corpus and a base feature set is obtained. The feature set contains characteristics ranging from low-level spectral and temporal acoustic features to high-level contextual features. The feature extraction process is discussed with particular emphasis on the interaction between acoustical and structural parameters. Statistical relations between audio features and emotional ratings from psychological experiments are systematically investigated. Finally, a linear model is created using the best features and the mean ratings and its prediction efficiency is evaluated and discussed.

UR - http://www.scopus.com/inward/record.url?scp=84905197646&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905197646&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84905197646

ER -