On feature selection in environmental sound recognition

Given a broad set of content-based audio features, we employ principal component analysis for the composition of an optimal feature set for environmental sounds. We select features based on quantitative data analysis (factor analysis) and conduct retrieval experiments to evaluate the quality of the...

Full description

Saved in:
Bibliographic Details
Main Authors: Mitrovic, D., Zeppelzauer, M., Eidenberger, H.
Format: Conference Proceeding
Language:English
Subjects:
Cepstral analysis
Data analysis
Environtmental Sound Recognition
Feature Selection
Fourier transforms
Frequency
Information retrieval
Linear predictive coding
Music information retrieval
Principal component analysis
Spatial databases
Speech recognition
Statistical Data Analysis
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Given a broad set of content-based audio features, we employ principal component analysis for the composition of an optimal feature set for environmental sounds. We select features based on quantitative data analysis (factor analysis) and conduct retrieval experiments to evaluate the quality of the feature combinations. Retrieval results show that statistical data analysis gives useful hints for feature selection. The experiments show the importance of feature selection in environmental sound recognition.
ISSN:1334-2630