Study of soundscape emotions alteration by a blend of music signals

Stone Cheng, Shi Shiang Niu, Cheng Kai Hsu

Research output: Contribution to conferencePaperpeer-review

Abstract

This study presents an approach for analyzing the ingredient of emotions aroused by the music signals, and applied to the soundscape emotions analysis. The proposed system integrated variety of emotion models, including two-dimensional emotion space. Training process for emotion recognition is preceded in a variety of features by 192 music clips to build emotional classification model between each other in order to construct two dimensional analysis of the emotive states. Eleven features are extracted into music and audio categories. Each feature used different length of frame for analysis. The proposed system classified the category of four emotions in the emotion plane by support vector machine (SVM), and draws the variation of emotion ingredients evoked by musical signals. A Gaussian mixture model (GMM) is used to demarcate the boundaries of "Exuberance", "Contentment", "Anxious", and "Depression" on the emotion plane. A graphic interface of emotion arousal locus on two-dimensional model of mood is established to represent the tracking of emotional transition. The soundscape survey procedure is carried out by studying the soundscape emotion locus tracking on selected soundscape sets to evaluate the effectiveness of emotions alteration by a blended music signals. Preliminary evaluations indicate that the proposed algorithms produce results agreed well.

Original languageEnglish
Pages4770-4777
Number of pages8
StatePublished - 21 Aug 2016
Event45th International Congress and Exposition on Noise Control Engineering: Towards a Quieter Future, INTER-NOISE 2016 - Hamburg, Germany
Duration: 21 Aug 201624 Aug 2016

Conference

Conference45th International Congress and Exposition on Noise Control Engineering: Towards a Quieter Future, INTER-NOISE 2016
CountryGermany
CityHamburg
Period21/08/1624/08/16

Keywords

  • Gaussian mixture model (GMM)
  • Music emotion
  • Soundscape
  • Support vector machine (SVM)

Fingerprint Dive into the research topics of 'Study of soundscape emotions alteration by a blend of music signals'. Together they form a unique fingerprint.

Cite this