Grant: Engage Grants Program
University of Victoria
$24,999.00
Content-aware music recommender system using emotion recognition
FY 2016-17
Summary
Imagine you were in charge of the new television commercial on how NSERC research grants led to importantscientific breakthroughs, high returns on investment and new jobs for Canada. Advertising sits at the nexus ofinformation and emotion, and a well known shortcut to convey emotion is music. How would you describe themusic you want to use in this ad? As something aspirational? Or uplifting? But: what is aspirational music?Something like 'Clocks' by Coldplay? Bach's 'Prelude No 1'? Or 'Shake It Out' by Florence and The Machine?Typically, advertisement agencies have only a few weeks to deliver a product, and budget constraints do notalways allow for original music or expensive licensing fees. Apollo Music Store (AMS) specializes in curatingand licensing music to fulfill the needs of advertising agencies and brands around the world. Their musiccurators have carefully annotated each song of their library with multiple labels to allow efficient queries.Advertisers often have a clear idea of what emotion they want the music to convey in their ads, but lack themusical vocabulary to clearly define it. Allowing them to query the library using an example song instead ofwords would alleviate this problem. The aim of this project is to design, develop and evaluate machine learningalgorithms for the automated recommendation of music, based on the emotional and acoustic similarities to anaudio example provided by the user. This project combines the quest to understand human emotions withmachine learning techniques and music theory, and thus has far reaching applications in affective computing,cognitive science and artificial intelligence research.
Program
Engage Grants Program
Recipient
Location
British Columbia, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
505519-2016
Name nom
Stege, Ulrike
Department département
Computer Science
Organization id
7
Institution établissement
University of Victoria
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2016
Competition year année de concours
2016
Award amount
24999
Program id
EGP
Program name en
Engage Grants Program
Program name fr
Programme de subventions d'engagement partenariat
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1554
Committee name en
Pacific Internal Decision Committee
Committee name fr
Comité de décision interne pour le Pacifique
Area of application code
1207
Area of application group en
Advancement of knowledge
Area of application group fr
Avancement des connaissances
Area of application en
Information, computer and communication technologies
Area of application fr
Technologie de l'information, des ordinateurs et des réseaux de communications
Research subject code
2713
Research subject group en
Information technology
Research subject group fr
Technologie de l'information
Research subject en
Algorithms
Research subject fr
Algorithmes
Partie
1
Nb partie
1
Application title
Content-aware music recommender system using emotion recognition
Keyword
NSERC
Application summary
Imagine you were in charge of the new television commercial on how NSERC research grants led to importantscientific breakthroughs, high returns on investment and new jobs for Canada. Advertising sits at the nexus ofinformation and emotion, and a well known shortcut to convey emotion is music. How would you describe themusic you want to use in this ad? As something aspirational? Or uplifting? But: what is aspirational music?Something like 'Clocks' by Coldplay? Bach's 'Prelude No 1'? Or 'Shake It Out' by Florence and The Machine?Typically, advertisement agencies have only a few weeks to deliver a product, and budget constraints do notalways allow for original music or expensive licensing fees. Apollo Music Store (AMS) specializes in curatingand licensing music to fulfill the needs of advertising agencies and brands around the world. Their musiccurators have carefully annotated each song of their library with multiple labels to allow efficient queries.Advertisers often have a clear idea of what emotion they want the music to convey in their ads, but lack themusical vocabulary to clearly define it. Allowing them to query the library using an example song instead ofwords would alleviate this problem. The aim of this project is to design, develop and evaluate machine learningalgorithms for the automated recommendation of music, based on the emotional and acoustic similarities to anaudio example provided by the user. This project combines the quest to understand human emotions withmachine learning techniques and music theory, and thus has far reaching applications in affective computing,cognitive science and artificial intelligence research.