Robust Sound Modeling for Song Identification in Broadcast Audio

摘要

This paper describes the development of an audio fingerprint called AudioDNA designed to be robust againstseveral distortions including those related to radio broadcasting. A complete system, covering also a fast andefficient method for comparing observed fingerprints against a huge database with reference fingerprints isdescribed. The promising results achieved with the first prototype system observing music titles as well ascommercials are presented.