Scalable and robust audio fingerprinting method tolerable to time-stretching

A time-stretching invariant, robust audio fingerprinting method, based on landmarks in the audio spectrogram is proposed in this paper. Time-stretching of audio clips or songs are done to evade copyright detection as most of the fingerprinting techniques are time dependent. Time-stretching is also used in music industry to produce remix & song mash-ups and in multimedia broadcasting to fit content within the required duration. The proposed algorithm is based on the audio hashing of frequency peaks in the spectrogram. It is scalable and tolerant to time-stretching. The experiment results show the method is highly tolerable to time-stretch than the state-of-the-art Shazam's audio fingerprinting.