이중 주파수 대역 검출기반의 강인한 Audio Fingerprinting 시스템

Abstract

In this paper, we present a new audio identification system which is robust to various attacks. The types of attacks employed are modification such as changes of tempo, pitch and speed and noise addition also low and high pass filtering. We proposed a two-dimensional representation for the audio signal called FFMAP. This consists of pitch components and frame components. We also employ Pearson’s correlation score to calculate similarity between original audio data and query. Experimental results show that the proposed algorithm has a high performance.