Effective Digital Music Retrieval System through Content-based Features
In this paper, we propose effective system for digital music retrieval. We divided proposed system into Client and Server. Client part consists of pre-processing and Content-based feature extraction stages. In pre-processing stage, we minimized Time code Gap that is occurred among same music contents. As content-based feature, first-order differentiated MFCC were used. These presented approximately envelop of music feature sequences. Server part included Music Server and Music Matching stage. Extracted features from 1,000 digital music files were stored in Music Server. In Music Matching stage, we found retrieval result through similarity measure by DTW. In experiment, we used 450 queries. These were made by mixing different compression standards and sound qualities from 50 digital music files. Retrieval accurate indicated 97% and retrieval time was average 15ms in every single query. Out experiment proved that proposed system is effective in retrieve digital music and robust at various user environments of web.
[1] Z. Jun, S. Kwong, W. Gang, and Q. Hong, "Using Mel-Frequency
Cepstral Coefficients in Missing Data Technique," EURASIP Journal on
Applied Signal Processing, Vol.3, 2004, pp. 340-346.
[2] M. Xu, NC. Maddage, C. Xu, M. Kankanhalli, and Q.Tian, "Creating
audio keywords for event detection in soccer video," Proc. International
Conference Multimedia and Expo ICME-03, Baltimore, USA, 2003, pp.
281-284.
[3] B.J. Shannon, and K.K. Paliwal, "A Comparative study of filter bank
spacing for speech recognition," Proc. International Microelctronic
engineering research conference, Brisbane, AUSTRALIA, 2003, pp. 1-3.
[4] Ziyou Xiong, R. Radhakrishnana, A. Divakaran, and T.S. Huang,
"Comparing MFCC and MPEG-7 Audio features for feature extraction,
maximum likelihood HMM and entropic priop HMM for sports audio
classification," Proc. International Conference Multimedia and Expo
ICME-03, Baltimore, USA, 2003, pp. 397-400.
[5] J.C. Brown, A. Hodgins-Davis, and P.J.O. Miller, "Classification of
vocalizations of killer whales using dynamic time warping," The Journal
of the Accoustical Society of America, Vol.119, 2006, pp. EL34-EL40.
[6] C.A. Ratanamahatana, and E. Keogh, "Three myths about dynamic time
warping data mining," Proc. SIAM International Conference on Data
Mining, Newport Beach, CA, 2005, pp. 506-510.
[7] A.M. Youssef, T.K. Abdel-Galil, E.F. El-Saadany, and M.M.A. Salama,
"Disturbance classification utilizing dynamic time warping classifier,"
IEEE Transactions on Power Delivery, Vol. 19, 2004, pp. 272-278.
[8] A. Pikrakis, S. Theodoridis, and D. Kamarotos, "Recognition of isolated
musical patterns using context dependent dynamic time warping," IEEE
Speech and Audio Processing, Vol. 11, 2003, pp. 175-183.
[9] E.J. Keogh, and M.J. Pazzani, "Computer Derivative Dynamic Time
Warping," Proc. First SIAM International Conference on Data Mining,
Chicago, USA, 2001, pp. 1-11.
[10] S. Velusamy, B. Thoshkahna, and K.R. Ramakrishnan, "A Novel Melody
Line Identification Algorithm for Polyphonic MIDI Music," Proc. LNCS
Advances in Multimedia Modeling, 2006, pp. 248-257.
[11] Ning Hu, R.B. Dannenberg, and G. Tzanetakis, Polyphonic audio
matching and alignment for music retrieval. Proc. 2003 IEEE Workshop
on Application of Signal Processing to Audio and Acoustics, New York,
USA, 2003, pp. 185-188.
[12] R. Clifford, M. christodoulakis, and T. Crawford, "A Fast Randomised
Maximal Subset Matching Algorithm for Document-Level Music
Retrieval," Proc. 7th International Conference on Music Information
Retrieval, Victoria, CA, 2006.
[13] Y.Y. Chung, H.c. Choi, Zhen Zhao, M.A.M. Shukran, Y.S. David, and
Fang Chen, "An Efficient tree-based quantization for content based music
retrieval system," Proc. 2007 annual Conference on International
Conference on Computer Engineering and Applications table of contents,
Queensland, AUSTRALIA, 2007, pp. 237-241.
[14] A. Spanias, T. Painter, V. Atti, and J.V. Candy, Audio Signal Processing
and Coding (The Journal of the Acoustical Society of America, 2007).
[15] G. Peeters, "Music Pitch Representation by Periodicity Measures Based
on Combined Temporal and Spectral Representations," Proc. 2006 IEEE
International Conference on Acoustics, Speech and Signal Processing,
Toulouse, FRANCE, 2006, pp. V53-V56.
[16] Xin Zhang, and W. Ras Zbigniew, "Analysis of Sound Features for Music
Timbre Recognition," Proc. 2007 International Conference on
Multimedia and Ubiquitous Engineering, Seoul, Korea, 2007.
[17] J.P. Bello, and J. Pickens, "A robust mid-level representation for
harmonic content in music signals," Proc. International Symposium on
Music Information Retrieval 2005, London, UK, 2005.
[18] M. Marolt, "Melody-based retrieval in audio collections," The Journal of
the Acoustical Society of America, Vol. 122, No. 5, 2007.
[19] Xi Shao, N.C. Maddage, Xu Changsheng, and M.S. Kankanhalli,
"Automatic music summarization based on music structure analysis,"
Proc. 2005 IEEE International Conf. on Acoustics, Speech, and Signal
Processing, Philadelphia, USA, 2005, pp. 1169-1172.
[20] Yi Yu, J. Stephen Downie, Lei Chen, Vincent Oria, and Kazuki Joe,
"Searching musical audio dataset by a batch of multi-variant tracks,"
Proc. The 1st ACM International Conference on Multimedia information
retrieval table of contents, Vancouver, CA, 2008, pp. 121-127.
[21] R. Hu, and R.I. Damper, "Fusion of two classifiers for speaker
identification: removing and not removing silence," Proc. 8th
International Conference on Information Fusion, Philadelphia, USA,
2005, pp. 429-436.
[22] Xufang Zhao, and D. O-Shaughnessy, "A new hybrid approach for
automatic speech signal segmentation using silence signal detection,
energy convex hull, and spectral variation," Proc. Canadian Conference
on Electrical and Computer Engineering, Ottawa, CA, 2008, pp.
145-148.
[23] Wenjuan Pan, Yong Yao, Zhijing Liu, and Weiyao Huang, "Audio
classification in a weighted SVM," Proc. International Symposium on
Communications and Information Technologies, Sydney, AUSTRALIA,
2007, pp. 468-472.
[1] Z. Jun, S. Kwong, W. Gang, and Q. Hong, "Using Mel-Frequency
Cepstral Coefficients in Missing Data Technique," EURASIP Journal on
Applied Signal Processing, Vol.3, 2004, pp. 340-346.
[2] M. Xu, NC. Maddage, C. Xu, M. Kankanhalli, and Q.Tian, "Creating
audio keywords for event detection in soccer video," Proc. International
Conference Multimedia and Expo ICME-03, Baltimore, USA, 2003, pp.
281-284.
[3] B.J. Shannon, and K.K. Paliwal, "A Comparative study of filter bank
spacing for speech recognition," Proc. International Microelctronic
engineering research conference, Brisbane, AUSTRALIA, 2003, pp. 1-3.
[4] Ziyou Xiong, R. Radhakrishnana, A. Divakaran, and T.S. Huang,
"Comparing MFCC and MPEG-7 Audio features for feature extraction,
maximum likelihood HMM and entropic priop HMM for sports audio
classification," Proc. International Conference Multimedia and Expo
ICME-03, Baltimore, USA, 2003, pp. 397-400.
[5] J.C. Brown, A. Hodgins-Davis, and P.J.O. Miller, "Classification of
vocalizations of killer whales using dynamic time warping," The Journal
of the Accoustical Society of America, Vol.119, 2006, pp. EL34-EL40.
[6] C.A. Ratanamahatana, and E. Keogh, "Three myths about dynamic time
warping data mining," Proc. SIAM International Conference on Data
Mining, Newport Beach, CA, 2005, pp. 506-510.
[7] A.M. Youssef, T.K. Abdel-Galil, E.F. El-Saadany, and M.M.A. Salama,
"Disturbance classification utilizing dynamic time warping classifier,"
IEEE Transactions on Power Delivery, Vol. 19, 2004, pp. 272-278.
[8] A. Pikrakis, S. Theodoridis, and D. Kamarotos, "Recognition of isolated
musical patterns using context dependent dynamic time warping," IEEE
Speech and Audio Processing, Vol. 11, 2003, pp. 175-183.
[9] E.J. Keogh, and M.J. Pazzani, "Computer Derivative Dynamic Time
Warping," Proc. First SIAM International Conference on Data Mining,
Chicago, USA, 2001, pp. 1-11.
[10] S. Velusamy, B. Thoshkahna, and K.R. Ramakrishnan, "A Novel Melody
Line Identification Algorithm for Polyphonic MIDI Music," Proc. LNCS
Advances in Multimedia Modeling, 2006, pp. 248-257.
[11] Ning Hu, R.B. Dannenberg, and G. Tzanetakis, Polyphonic audio
matching and alignment for music retrieval. Proc. 2003 IEEE Workshop
on Application of Signal Processing to Audio and Acoustics, New York,
USA, 2003, pp. 185-188.
[12] R. Clifford, M. christodoulakis, and T. Crawford, "A Fast Randomised
Maximal Subset Matching Algorithm for Document-Level Music
Retrieval," Proc. 7th International Conference on Music Information
Retrieval, Victoria, CA, 2006.
[13] Y.Y. Chung, H.c. Choi, Zhen Zhao, M.A.M. Shukran, Y.S. David, and
Fang Chen, "An Efficient tree-based quantization for content based music
retrieval system," Proc. 2007 annual Conference on International
Conference on Computer Engineering and Applications table of contents,
Queensland, AUSTRALIA, 2007, pp. 237-241.
[14] A. Spanias, T. Painter, V. Atti, and J.V. Candy, Audio Signal Processing
and Coding (The Journal of the Acoustical Society of America, 2007).
[15] G. Peeters, "Music Pitch Representation by Periodicity Measures Based
on Combined Temporal and Spectral Representations," Proc. 2006 IEEE
International Conference on Acoustics, Speech and Signal Processing,
Toulouse, FRANCE, 2006, pp. V53-V56.
[16] Xin Zhang, and W. Ras Zbigniew, "Analysis of Sound Features for Music
Timbre Recognition," Proc. 2007 International Conference on
Multimedia and Ubiquitous Engineering, Seoul, Korea, 2007.
[17] J.P. Bello, and J. Pickens, "A robust mid-level representation for
harmonic content in music signals," Proc. International Symposium on
Music Information Retrieval 2005, London, UK, 2005.
[18] M. Marolt, "Melody-based retrieval in audio collections," The Journal of
the Acoustical Society of America, Vol. 122, No. 5, 2007.
[19] Xi Shao, N.C. Maddage, Xu Changsheng, and M.S. Kankanhalli,
"Automatic music summarization based on music structure analysis,"
Proc. 2005 IEEE International Conf. on Acoustics, Speech, and Signal
Processing, Philadelphia, USA, 2005, pp. 1169-1172.
[20] Yi Yu, J. Stephen Downie, Lei Chen, Vincent Oria, and Kazuki Joe,
"Searching musical audio dataset by a batch of multi-variant tracks,"
Proc. The 1st ACM International Conference on Multimedia information
retrieval table of contents, Vancouver, CA, 2008, pp. 121-127.
[21] R. Hu, and R.I. Damper, "Fusion of two classifiers for speaker
identification: removing and not removing silence," Proc. 8th
International Conference on Information Fusion, Philadelphia, USA,
2005, pp. 429-436.
[22] Xufang Zhao, and D. O-Shaughnessy, "A new hybrid approach for
automatic speech signal segmentation using silence signal detection,
energy convex hull, and spectral variation," Proc. Canadian Conference
on Electrical and Computer Engineering, Ottawa, CA, 2008, pp.
145-148.
[23] Wenjuan Pan, Yong Yao, Zhijing Liu, and Weiyao Huang, "Audio
classification in a weighted SVM," Proc. International Symposium on
Communications and Information Technologies, Sydney, AUSTRALIA,
2007, pp. 468-472.
@article{"International Journal of Information, Control and Computer Sciences:62373", author = "Bokyung Sung and Kwanghyo Koo and Jungsoo Kim and Myung-Bum Jung and Jinman Kwon and Ilju Ko", title = "Effective Digital Music Retrieval System through Content-based Features", abstract = "In this paper, we propose effective system for digital music retrieval. We divided proposed system into Client and Server. Client part consists of pre-processing and Content-based feature extraction stages. In pre-processing stage, we minimized Time code Gap that is occurred among same music contents. As content-based feature, first-order differentiated MFCC were used. These presented approximately envelop of music feature sequences. Server part included Music Server and Music Matching stage. Extracted features from 1,000 digital music files were stored in Music Server. In Music Matching stage, we found retrieval result through similarity measure by DTW. In experiment, we used 450 queries. These were made by mixing different compression standards and sound qualities from 50 digital music files. Retrieval accurate indicated 97% and retrieval time was average 15ms in every single query. Out experiment proved that proposed system is effective in retrieve digital music and robust at various user environments of web.
", keywords = "Music Retrieval, Content-based, Music Feature and Digital Music.", volume = "3", number = "2", pages = "457-6", }
