Audio fingerprint parameterization for multimedia advertising identification

This article follows step by step a general framework for fingerprint extraction in order to develop a system for advertisements' monitoring. The parameterization process uses some spatial and spectral characteristics measured over 600 advertisements that contain various types of sounds. Key factors such as accuracy, process time, and granularity are analyzed together in order to enhance the system performance. At the end, the algorithm shows an accuracy of 99% using three seconds of granularity samples, and also the best compromise between processing time and performance is achieved. This study suggests a set of parameterization steps which could be successfully implemented in other related audio applications.