Song Clustering Using Similarity of Audio Fingerprint

Main Article Content

สุนันท์ ธาติ
พงศ์พันธ์ กิจสนาโยธิน
วรลักษณ์ คงเด่นฟ้า


Listening is the most common way to detect copyright infringement or identify unknown music data, but it is difficult to analyze a large amount of music data. The accuracy also depends on the listener's level of expertise. As mentioned earlier, music recognition is applied to solve this problem and the audio fingerprint is a widely used as data feature. Audio fingerprint analysis is effective at finding audio tracks which are duplicate content (exactly match) however it cannot detect in the case of similar content. This research proposes a method for finding the similarity between two songs using relation functions for comparing audio fingerprints instead of comparing bigger music content. For a case study, we try to find the original song from the cover song to assess the efficiency of our approach. The findings of this study indicate that proposed approach can be use effectively to identify the original song covered with many genres. Overall average area under curve (Average AUC) is 0.790.


Download data is not yet available.

Article Details

Research Article


J. S. Downie, "Music information retrieval," Annual Review of Information Science and Technology, vol. 37, pp. 295-340, 2003.

L. Tao and M. Ogihara, "Toward intelligent music information retrieval," IEEE Transactions on Multimedia, vol. 8, no. 3, pp. 564-574, 2006.

C. Ouali, P. Dumouchel, and V. Gupta, " A spectrogram-based audio fingerprinting system for content-based copy detection," Multimedia Tools and Application, vol. 75, no. 15, pp. 9145-9165, 2016.

D. Perrott and R. Gjerdingen, “Scanning the dial: An exploration of factors in the identification of musical style.,” in The 8th international conference on music perception & cognition, Evanston, Illinois, USA, 2004.

G. Tzanetakis and P. Cook, "Musical genre classification of audio signals," IEEE Transactions on Speech and Audio Processing, vol. 10, no. 15, pp. 293-302, 2002.

D. C. Correa and F. A. Rodrigues, "A survey on symbolic data-based music genre classification," Expert Systems with Applications, vol. 60, pp. 190-210, 2016.

V. Chandrasekhar, M. Sharifi, and D. A. Ross, “Survey and Evaluation of Audio Fingerprinting Schemes for Mobile Query-by-Example Applications.,” in the 12th International Society for Music Information Retrieval Conference, Miami, Florida, USA, 2011, pp. 801–806.

C. Ouali, P. Dumouchel, and V. Gupta, "Efficient spectrogram-based binary image feature for audio copy detection," in 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane Convention & Exhibition Centre Brisbane, Queensland, Australia, 2015, pp. 1792-1796.

“VOICEBOX: Speech Processing Toolbox for MATLAB.” [Online]. Available: [Accessed: 24-Feb-2017].

“MATLAB,” MathWorks. [Online]. Available: [Accessed: 24-Jan-2017].

W. B. Snow, "Audible Frequency Ranges of Music, Speech and Noise," The Journal of the Acoustical Society of America, vol. 3, no. 10, pp. 10-10, 1931.