Abstract
To date, common acoustic features such as MPEG-7 and Fourier/wavelet transform-based features have been frequently used for environmental sound classification. However, these transforms have difficulty dealing with specific properties of environmental sounds, due to their limited scopes. In this paper, we investigate three types of transforms as yet untried for this purpose, and show that they are more effective than traditional features. This result is mainly due to the fact that they have functionalities that were not easily treatable with traditional transforms. Experimental results show that the combination of these features with traditional features can achieve 86.09% of the maximum accuracy in environmental sound classification, compared to 74.35% of the maximum accuracy when confined to traditional features.
| Original language | English |
|---|---|
| Title of host publication | Proceedings - 2009 IEEE International Conference on Multimedia and Expo, ICME 2009 |
| Pages | 542-545 |
| Number of pages | 4 |
| DOIs | |
| Publication status | Published - 2009 Nov 20 |
| Event | 2009 IEEE International Conference on Multimedia and Expo, ICME 2009 - New York, NY, United States Duration: 2009 Jun 28 → 2009 Jul 3 |
Other
| Other | 2009 IEEE International Conference on Multimedia and Expo, ICME 2009 |
|---|---|
| Country | United States |
| City | New York, NY |
| Period | 09/6/28 → 09/7/3 |
Fingerprint
Keywords
- Discrete chirplet transform
- Discrete curvelet transform
- Discrete Hilbert transform
- Environmental sound recognition
- Feature extraction
ASJC Scopus subject areas
- Computer Graphics and Computer-Aided Design
- Computer Networks and Communications
- Hardware and Architecture
- Software