Personal tools

The Science and Technology of Music

Sections
Home Activities Student Colloquia Music Technology Cory McKay: "Combining Features Extracted from Audio, Symbolic, and Cultural Sources"

Skip to content. | Skip to navigation

Cory McKay: "Combining Features Extracted from Audio, Symbolic, and Cultural Sources"

PLEASE NOTE THAT THIS TALK WILL TAKE PLACE AT 4:30PM INSTEAD OF 12:30PM. Cory McKay is a Doctoral student in the Music Technology Area of the Schulich School of Music, McGill University.

What
  • Music Technology Student Colloquium
When Sep 30, 2008
from 04:30 PM to 05:30 PM
Where New Music Building, McGill University, 527 Sherbrooke St. West, A512 (in the library - entrance on 3rd floor)
Add event to calendar vCal
iCal

Please note that this talk will take place at 4:30pm instead of 12:30pm.

This research experimentally investigated the classification utility of combining features extracted from separate audio, symbolic and cultural sources of musical information. This was done via a series of genre classification experiments performed using all seven possible combinations and subsets of the three corresponding types of features.


These experiments were performed using jMIR, a software suite designed for use both as a toolset for performing MIR research and as a platform for developing and sharing new algorithms.


The experimental results indicated that combining feature types can indeed substantively improve classification accuracy. Accuracies of 96.8% and 78.8% were attained respectively on 5 and 10-class genre taxonomies when all three feature types were combined, compared to average respective accuracies of 85.5% and 65.1% when features extracted from only one of the three sources of data were used. It was also found that combining feature types decreased the seriousness of those misclassifications that were made, on average, particularly when cultural features were included.

Document Actions