Music Recommendation System

• Autorzy: Hoffmann P. , Kaczmarek A. , Spaleniak P. , Kostek B.
• Języki publikacji: EN

Abstrakty

EN

The paper focuses on optimization vector content feature for the music recommendation system. For the purpose of experiments a database is created consisting of excerpts of music files. They are assigned to 22 classes corresponding to different music genres. Various feature vectors based on low-level signal descriptors are tested and then optimized using correlation analysis and Principal Component Analysis (PCA). Results of the experiments are shown for the variety of feature vectors. Also, a music recommendation system is presented along with its main user interfaces.

Słowa kluczowe

EN

feature vectors; music classification; music information retrieval; music parametrization; principal component analysis

• Wydawca: Instytut Łączności - Państwowy Instytut Badawczy
• Czasopismo: Journal of Telecommunications and Information Technology
• Rocznik: 2014
• Tom: nr 2
• Strony: 59--69
• Opis fizyczny: Bibliogr. 33 poz., rys., tab.

Twórcy

autor

Hoffmann P.

• Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology, Gdańsk, Poland

autor

Kaczmarek A.

• Multimedia Systems Department, Gda«sk University of Technology, Gdańsk, Poland

autor

Spaleniak P.

• Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology, Gdańsk, Poland

autor

Kostek B.

• Faculty of Electronics, Telecommunications and Informatics, Gdańsk University of Technology, Gdańsk, Poland

Bibliografia

• [1] J.-J. Aucouturier and F. Pachet, "Representing musical genre: A state of art", J. New Music Res., vol. 32, no. 1, pp. 83-93, 2003.
• [2] J. Benesty, M. Mohan Sondhi, and H. Yiteng, Springer Handbook of Speech Processing. Berlin Heidelberg: Springer, 2008.
• [3] S. Ewert, "Signal processing methods for music, synchronization, audio matching, and source separation", Ph.D. thesis, Friedrich-Wilhelms University, Bonn, Germany, 2012.
• [4] P. Hoffmann, B. Kostek, A. Kaczmarek, and P. Spaleniak, "Creating a reliable music discovery and recommendation system", in Synat Workshop SYNAT 2013, Warsaw, Poland, 2013, Studies in Computational Intelligence, Springer (in print).
• [5] P. Hoffmann, B. Kostek, A. Kaczmarek, and P. Spaleniak, "Wyszukiwarka Nagrań muzycznych - Serwis muzyczny Synat", Telecom. Review, no. 8-9, 2013 (in Polish).
• [6] A. Holzapfel and Y. Stylianou, "Musical genre classification using nonnegative matrix factorization-based features", IEEE Trans. Audio, Speech, Lang. Proces., vol. 16, no. 2, pp. 424-434, 2008.
• [7] K. Hyoung-Gook, N. Moreau, and T. Sikora, MPEG-7 Audio and Beyond: Audio Content Indexing and Retrieval. Wiley, 2005.
• [8] J. P. Bello, "Low-level features and timbre, MPATE-GE 2623 Music Information Retrieval", New York University [Online]. Available: http://www.nyu.edu/classes/bello/MIR_files/timbre.pdf
• [9] D. Jang, M. Jin, and C. D. Yoo, "Music genre classification using novel features and a weighted voting method", in Proc. IEEE Int. Conf. Multimed. Expo ICME 2008, Hanover, Germany, 2008, pp. 1377-1380.
• [10] Kappa Coeficient [Online]. Available: http://statsoft.pl/czytelnia/artykuly/Krzywe ROC czyli ocena jakosci.pdf
• [11] B. Kostek, "Content-based approach to automatic recommendation of music", in Proc. 131st Audio Engin. Soc. Convention, New York, NY, USA, 2011.
• [12] B. Kostek, "Music information retrieval in music repositories", in Rough Sets and Intelligent Systems - Professor Zdzisław Pawlak in Memoriam, Z. Suraj and A. Skowron, Eds. Intelligent Systems Reference Library, vol. 42, pp. 463-489. Berlin Heidelberg: Springer, 2013.
• [13] B. Kostek, Perception-Based Data Processing in Acoustics - Applications to Music Information Retrieval and Psychophysiology. Studies in Computational Intelligence, vol. 3. Berlin Heidelberg: Springer, 2005.
• [14] B. Kostek, Soft Computing in Acoustics, Applications of Neural Networks, Fuzzy Logic and Rough Sets to Musical Acoustics. Studies in Fuzziness and Soft Computing. Heildelberg New York: Physica Verlag, 1999.
• [15] B. Kostek and A. Czyzewski, "Representing musical instrument sounds for their automatic classification", J. Audio Engin. Soc., vol. 49, pp. 768{785, 2001.
• [16] B. Kostek and Ł. Kania, "Music information analysis and retrieval techniques", Archiv. of Acoust., vol. 33, no. 4, pp. 483-496, 2008.
• [17] B. Kostek et al., "Report of the ISMIS 2011 Contest: Music Information Retrieval, Foundations of Intelligent Systems", in Proc. 19th Int. Symp. Methodol. Intell. Sys. ISMIS 2011, Warsaw, Poland, 2011. Springer, 2011, pp. 715{724.
• [18] Lastfm [Online]. Available: http://www.last.fm/
• [19] T. Li, M. Ogihara, and Q. Li, "A comparative study on content-based music genre classfication", in Proc. 26th Ann. Int. ACM SIGIR Conf. Res. Develop. Inform. Retriev., Toronto, Canada, 2003, pp. 282-289.
• [20] T. Lidy, A. Rauber, A. Pertusa, and J. Inesta, "Combining audio and symbolic descriptors for music classification from audio", Music Information Retrieval Information Exchange (MIREX), 2007.
• [21] A. Lindsay and A. Herre, "MPEG-7 and MPEG-7 audio - an overview", J. Audio Engin. Soc., vol. 49, no. 7-8, pp. 589-594, 2001.
• [22] M. Mandel and D. Ellis, "LABROSA's audio music similarity and classification submissions", Music Information Retrieval Information Exchange (MIREX), 2007.
• [23] Music store Amazon [Online]. Available: http://www.amazon.com/
• [24] Music store Itunes [Online]. Available: https:// www.apple.com/pl/itunes/
• [25] E. Panagakis, E. Benetos, and C. Kotropoulos, "Music genre classification: a multilinear approach", in Proc. 9th Int Conf Music Inform Retriev ISMIR 2008, Philadelphia, PA, USA, 2008, pp. 583-88.
• [26] Pandora [Online]. Available: http://www.pandora.com
• [27] P. Symeonidis, P. Ruxanda, A. Nanopoulos, and Y. Manolopoulos, "Ternary semantic analysis of social tags for personalized music recommendation", in Proc. 9th Int Conf Music Inform Retriev ISMIR 2008, Philadelphia, PA, USA, 2008, pp. 219-224.
• [28] ISMIR - The International Society for Music Information Retrieval, International Conference on Music Information Retrieval [Online]. Available: http://www.ismir.net/
• [29] G. Tzanetakis and P. Cook, "Musical genre classification of audio signal", IEEE Trans Speech and Audio Proces., vol. 10, no. 5, pp. 293-302, 2002.
• [30] G. Tzanetakis, G. Essl, and P. Cook, "Automatic musical genre classification of audio signals", in Proc. Int. Symp. Music Inform. Retriev. ISMIR 2001, Bloomington, USA, 2001.
• [31] Varence website [Online]. Available: http://www.verance.com/
• [32] L. J. Williams and H. Abdi, "Principal component analysis", Wiley Interdiscip. Rev. Computat. Statis., vol. 2, no. 4, pp. 433-459, 2010.
• [33] P. Żwan and B. Kostek, "System for automatic singing voice recognition", J. Audio Engin. Soc., vol. 56, no. 9, pp. 710-723, 2008.