Paper Info
Title
Waveprint: Efficient wavelet-based audio fingerprinting
Abstract
In this paper, we present Waveprint, a novel method for audio identification. Waveprint uses a combination of computer-vision techniques and large-scale data-stream processing algorithms to create compact fingerprints of audio data that can be efficiently matched. The resulting system has excellent identification capabilities for small snippets of audio that have been degraded in a variety of manners, including competing noise, poor recording quality and cell-phone playback. We explicitly measure the tradeoffs between performance, memory usage, and computation through extensive experimentation. The system is more efficient in terms of memory usage and computation, while being more accurate when compared with previous state of the art systems. The applications of Waveprint include song identification for end-consumer use, copyright protection for audio assets, copyright protection for television assets and synchronization of off-line audio sources, such as live television.
Year
DOI
Venue
2008
10.1016/j.patcog.2008.05.006
Pattern Recognition
Keywords
Field
DocType
audio data,memory usage,audio identification,art system,audio retrieval,excellent identification capability,live television,audio asset,song identification,applications,copyright protection,off-line audio source,pattern analysis,image/video retrieval,efficient wavelet-based audio fingerprinting,computer vision
Signal processing,Synchronization,Information protection policy,Image retrieval,Speech recognition,Sound quality,System identification,Mathematics,Copy protection,Wavelet
Journal
Volume
Issue
ISSN
41
11
Pattern Recognition
Citations 
PageRank 
References 
40
1.94
14
Authors
2
Name
Order
Citations
PageRank
Shumeet Baluja14053728.83
Michele Covell270678.42