Audio fingerprint based on power spectral density and hamming distance measure

Song recognition is the process of identifying a song segment either from a digital or an analogue audio source. This has led to the necessity to identify songs within a database that consists of a very high number of songs compared to previous years. In this paper, a framework for audio fingerprint extraction based on Power Spectral Density is presented and performing recognition using hamming distance measure. Then, evaluating the performance of the proposed method using a scoring measure based on accuracy classification.