DMCA
Study of MPEG-7 Sound Classification and Retrieval
| Citations: | 1 - 0 self |
BibTeX
@MISC{Kim_studyof,
author = {Hyoung-gook Kim and Edgar Berdahl and Thomas Sikora},
title = {Study of MPEG-7 Sound Classification and Retrieval},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this paper, we present a comparison of three audio taxonomy methods for MPEG-7 sound classification. The MPEG-7 sound classification and indexing tools consist of both low-level and high-level description schemes. For the low-level descriptors that we use, low-dimensional features based on spectral basis descriptors are produced in three stages: normalized audio spectrum envelope, principal component analysis, and independent component analysis. High-level description schemes are used thereafter to describe the modeling of audio features, the procedure of audio classification, and retrieval. For classification we test three approaches: the direct approach, the hierarchical approach without hints, and the hierarchical approach with hints. Our experimental results show that the best approach is the hierarchical approach with hints, which results in a classification accuracy of around 99%. The direct approach produces the second best results, and the hierarchical approach without hints the third best results. 1
Keyphrases
mpeg-7 sound classification hierarchical approach high-level description scheme direct approach audio classification audio spectrum envelope spectral basis descriptor indexing tool consist low-level descriptor audio feature independent component analysis principal component analysis classification accuracy experimental result low-dimensional feature audio taxonomy method
