BROWSE
Detail
Journal Article
Audio Fingerprinting Based on Normalized Spectral Subband Moments
Cited 54 time in 
Download 2 time
Share 
Download 2 time
Share
- Authors
- Jin S. Seo, Min Ho Jin, Sun Il Lee, Dal Won Jang, Seung Jae Lee, Chang D. Yoo
- Issue Date
- 2006-04
- Citation
- IEEE Signal Processing Letters, v.13, no.4, pp.209-212
- ISSN
- 1070-9908
- Publisher
- IEEE
- Language
- English
- Type
- Journal Article
- Project Code
- 06MC1100, Technology of Contents Protection for Contents Distribution based on Multi-Platform, Suh Young Ho
- Abstract
- The performance of a fingerprinting system, which is often measured in terms of reliability and robustness, is directly related to the features that the system uses. In this letter, we present a new audio-fingerprinting method based on the normalized spectral subband moments. A threshold used to reliably determine a fingerprint match is obtained by modeling the features as a stationary process. The robustness of the normalized moments was evaluated experimentally and compared with that of the spectral flatness measure. Among the considered subband features, the first-order normalized moment showed the best performance for fingerprinting. © 2006 IEEE.
- KSP Keywords
- Audio fingerprinting, Best performance, Fingerprint match, Fingerprinting method, Reliability and robustness, Spectral flatness measure, Stationary process, first-order