SLIDE 1
Computational tools for knowledge-driven music browsing Gopala - - PowerPoint PPT Presentation
Computational tools for knowledge-driven music browsing Gopala - - PowerPoint PPT Presentation
Computational tools for knowledge-driven music browsing Gopala Krishna Koduri, Xavier Serra {gopala.koduri, xavier.serra}@upf.edu Music Technology Group Universitat Pompeu Fabra Barcelona, Spain Part - I THE CURRENT STATE OF THE AFFAIRS
SLIDE 2
SLIDE 3
Data Sources
SLIDE 4
Data Sources
SLIDE 5
Data Structuring
SLIDE 6
Data Structuring
SLIDE 7
Data Structuring
SLIDE 8
Data Structuring
SLIDE 9
Entities
- Also geographical regions, lineage etc…
SLIDE 10
How do we use this data?
SLIDE 11
Browsing the collections
SLIDE 12
Similarity measures for exploration
SLIDE 13
Application Programming Interface
SLIDE 14
WORK IN PROGRESS
Part - II
SLIDE 15
Limitations: Disconnected sources
SLIDE 16
Limitations: Simplistic similarity
SLIDE 17
Next steps
- Linking data sources
– More insights! – Provenance and Trust
- Machine-readable descriptions
SLIDE 18
Linked data example: Facebook
SLIDE 19
Linked data example: Google
SLIDE 20
How do they do it?
SLIDE 21
Machine readable descriptions
SLIDE 22
Machine readable descriptions
- Definition
- Classification
- Association
- …
Semantics
SLIDE 23
Semantics of musical concepts: raaga
SLIDE 24
Semantics of musical concepts: raaga
SLIDE 25
Knowledge from community data
Raaga Relation between raagas Musical form
SLIDE 26
What do all these entail?
- List all the performances of Bhairavi and it’s
allied raagas, of artists from Semmangudi’s lineage, at the music academy.
- What are the distinguishing phrases of
Pantuvarali raaga in the performances of artists from X and Y regions?
SLIDE 27
The ultimate goal
Data gathering Audio analysis Data structuring Musicological validation Music exploration User profjling
A data repository with varied sources
- MusicBrainz, Wikipedia, Kutcheris.com
- Outputs from audio analysis
- Semantic descriptions of musical concepts
- Knowledge extracted from user generated data
SLIDE 28