Environmental Sound Classification using Hybrid SVM/KNN Classifier and MPEG-7 Audio Low-Level Descriptor
The 2006 IEEE International Joint Conference on Neural Network Proceedings (2006)
- ISBN: 0780394909
- DOI: 10.1109/IJCNN.2006.1716317
Available from ieeexplore.ieee.org
or
Abstract
In this paper, we present a new environmental sound classification architecture. The proposed sound classifier is performed in frame level and fuses the support vector machine (SVM) and the k nearest neighbor rule MPEG-7 audio (KNN). In low-level feature selection, three descriptors, spectrum centroid, spectrum spread, and spectrum flatness are used as the sound features to exploit their ability in sound classification. rate. sound classifier features can achieve an 85.1% accuracy HMM using audio spectrum projection
Page 1
Environmental Sound Classification using Hybrid SVM/KNN Classifier and MPEG-7 Audio Low-Level Descriptor
Plain text is unavailable for this page.
Sign up today - FREE
Mendeley saves you time finding and organizing research. Learn more
- All your research in one place
- Add and import papers easily
- Access it anywhere, anytime
Start using Mendeley in seconds!
Readership Statistics
2 Readers on Mendeley
by Discipline
by Academic Status
50% Ph.D. Student
50% Researcher (at an Academic Institution)
by Country
50% Turkey
50% United States