Robust perceptual audio hashing

Robust audio hashing can be used for audio content identification in broadcast monitoring and database indexing applications. We propose novel robust audio hashing techniques in that, small changes in the source data (filtering, compression or AD/DA conversion etc.) do not cause any alteration on the hash sequences. In one scheme we use the periodicity property of the audio signals measured with correlation-based techniques. In a second scheme, the audio signal is converted into matrix form through mel frequency ceptsral coefficients (MFCC). The singular values of this matrix constitute the hash values of the signal of interest. Experiments performed involving several attacks have proven the robustness and specificity of the proposed methods.