Improving Music Mood Annotation Using Polygonal Circular Regression

Simple item page
dc.contributor.authorDufour, Isabelle
dc.contributor.supervisorTzanetakis, George
dc.contributor.supervisorCoady, Yvonne
dc.date.accessioned2015-08-31T20:36:13Z
dc.date.available2015-08-31T20:36:13Z
dc.date.copyright2015en_US
dc.date.issued2015-08-31
dc.degree.departmentDepartment of Computer Scienceen_US
dc.degree.levelMaster of Science M.Sc.en_US
dc.description.abstractMusic mood recognition by machine continues to attract attention from both academia and industry. This thesis explores the hypothesis that the music emotion problem is circular, and is a primary step in determining the efficacy of circular regression as a machine learning method for automatic music mood recognition. This hypothesis is tested through experiments conducted using instances of the two commonly accepted models of affect used in machine learning (categorical and two-dimensional), as well as on an original circular model proposed by the author. Polygonal approximations of circular regression are proposed as a practical way to investigate whether the circularity of the annotations can be exploited. An original dataset assembled and annotated for the models is also presented. Next, the architecture and implementation choices of all three models are given, with an emphasis on the new polygonal approximations of circular regression. Experiments with different polygons demonstrate consistent and in some cases significant improvements over the categorical model on a dataset containing ambiguous extracts (ones for which the human annotators did not fully agree upon). Through a comprehensive analysis of the results, errors and inconsistencies observed, evidence is provided that mood recognition can be improved if approached as a circular problem. Finally, a proposed multi-tagging strategy based on the circular predictions is put forward as a pragmatic method to automatically annotate music based on the circular model.en_US
dc.description.proquestcode0984en_US
dc.description.proquestcode0800en_US
dc.description.proquestcode0413en_US
dc.description.proquestemailzazz101@hotmail.comen_US
dc.description.scholarlevelGraduateen_US
dc.identifier.urihttp://hdl.handle.net/1828/6613
dc.languageEnglisheng
dc.language.isoenen_US
dc.rightsAvailable to the World Wide Weben_US
dc.subjectPolygonal Circular Regressionen_US
dc.subjectAutomatic Mood Classificationen_US
dc.subjectAudio Featuresen_US
dc.subjectMusic Information Retrieval (MIR)en_US
dc.subjectMusic Emotion Recognition (MER)en_US
dc.subjectMachine Learningen_US
dc.subjectMood annotationen_US
dc.subjectContent-based audioen_US
dc.subjectvalence-arousalen_US
dc.subjectAffective computingen_US
dc.subjectCircular regressionen_US
dc.subjectEmotion recognitionen_US
dc.subjectCircular modelen_US
dc.titleImproving Music Mood Annotation Using Polygonal Circular Regressionen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Dufour_Isabelle_MSc_2015.pdf
Size:
1.82 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.74 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

ETD (Electronic Theses and Dissertations)
Theses (Computer Science)
 
University of Victoria Libraries

We acknowledge and respect the Lək̓ʷəŋən (Songhees and Esquimalt) Peoples on whose territory the university stands, and the Lək̓ʷəŋən and W̱SÁNEĆ Peoples whose historical relationships with the land continue to this day.