Music Genre Determination Using Audio Fingerprinting

This paper compares two audio spotting methods: a feature-based audio classification method and a hashing method for audio fingerprinting. Moreover, the music genre determination performance of the methods is investigated. In this context, advantages and disadvantages of these methods are discussed and the audio identification performance of both methods are reported. Robustness to a number of attacks is also investigated. It is concluded that the performance of audio fingerprinting system outperforms the feature-based classification under the i.i.d. noise, mp3 compression and resampling attacks. However, the feature-based classification provides a higher detection accuracy under the time compression attack. Both systems are robust to synchronization attacks which is important for broadcast monitoring applications

[1]  C.-C. Jay Kuo,et al.  Audio content analysis for online audiovisual data segmentation and classification , 2001, IEEE Trans. Speech Audio Process..

[2]  Ton Kalker,et al.  A Highly Robust Audio Fingerprinting System With an Efficient Search Strategy , 2003 .

[3]  Shih-Fu Chang,et al.  Audio scene segmentation using multiple features, models and time scales , 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

[4]  Ton Kalker,et al.  A Highly Robust Audio Fingerprinting System , 2002, ISMIR.

[5]  George Tzanetakis,et al.  Multifeature audio segmentation for browsing and annotation , 1999, Proceedings of the 1999 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics. WASPAA'99 (Cat. No.99TH8452).

[6]  Malcolm Slaney,et al.  Construction and evaluation of a robust multifeature speech/music discriminator , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.