Dynamic Neural Networks Applied to Optimized Music Recommendation

Laura Elena Gómez Sánchez¹, Humberto Sossa Azuela¹, Ricardo Barrón¹, Francisco Cuevas² y Julio F. Jiménez Vielma¹

¹ Centro de Investigación en Computación-IPN, Unidad Profesional Adolfo-López Mateos, Av. Juan de Dios Batiz s/n y M. Othon de Mendizábal, Zacatenco, México, DF. 07738, México (e-mail: lenis45@hotmail.com, hsossa@cic.ipn.mx, rbarron@cic.ipn.mx, jfvielma@cio.mx).

² Centro de Investigaciones en Óptica A.C. Loma del Bosque #115, Col. Lomas del Campestre CP. 37150, León, Gto. México (e-mail: fjcuevas@cio.mx).

Resumen

En este trabajo se presenta un método basado en la operación de las llamadas redes neuronales dinámicas (RND), para la recomendación musical optimizada. Las redes son entrenadas con las señales de cada melodía, y no con descriptores tradicionales. La propuesta fue probada con una base de datos compuesta por 1,000 melodías, a diferentes frecuencias de muestreo.

Palabras clave: Recuperación de información musical, red neuronal dinámica, descriptor musical.

Abstract

A method based on the operation of so called dynamic neural networks (DNN) for music recommendation is described. DNNs are trained with the signals of each melody and not with traditional descriptors. The method has been tested with a database composed of 1.200 melodies, at different sampling frequencies.

Key words: Music information retrieval, dynamic neural networks, musical descriptor.

DESCARGAR ARTÍCULO EN FORMATO PDF

REFERENCIAS

[1] F. Wiering, "Can humans benefit from music information retrieval?,"AMR'06, Proc. of the 4th international conference on Adaptive Multimedia Retrieval: User, Context and Feedback, Springer, 2007, p. 82-94.         [ Links ]

[2] K. Lemstrom, G.A. Wiggins and D. Meredith, "A three-layer approach for music retrieval in large databases," 2^nd International Symposium on Music Information Retrieval, Bloomington, USA, 2001, p. 13-14.         [ Links ]

[3] H. Hoashi and K. Matsumoto, "Personalization of user profiles for content-based music retrieval based on relevance feedback," Proceeding of the eleventh ACM international conference on Multimedia, New York, USA, 2003, p. 110-119.         [ Links ]

[4] H. Zhuge, "An inexact model matching approach and its applications," Journal of Systems and Software, 67 (3), 2003, p. 201-212.         [ Links ]

[5] E. Hwang and S. Rho, "FMF (fast melody finder): A web-based music retrieval system", Lecture Notes in Computer Science vol. 277. Springer, 2004, p. 179-192.         [ Links ]

[6] E. Hwang and S. Rho, FMF: "Query adaptive melody retrieval system," Journal of Systems and Software, 79 (1), 2006, p. 43-56.         [ Links ]

[7] N. Ali, M. Mshtaq, "Hybrid query by humming and metadata search system (HQMS) analysis over diverse features," International Journal of Advanced Computer Science and Applications, Vol. 2, No. 9, 2011, p. 58.         [ Links ]

[8] P. W. Bertin-Mahieux, B. Whitman, P. Lameré, "The Million SongDataset," 12th Conference of International Society for MusicInformation Retrieval (ISMIR 2011), 2011.         [ Links ]

[9] C. McKay, D. Bainbridge, D, "A Musical Web Mining and AudioFeature Extraction Extension to the Greenstone Digital LibrarySoftware," 12th Conference of International Society for MusicInformation Retrieval (ISMIR 2011), 2011.         [ Links ]

[10] M. Weigl And C. Guastavino, "User Studies in the Music InformationRetrieval Literature," 12th Conference of International Society forMusic Information Retrieval (ISMIR 2011), 2011.         [ Links ]

[11] M. Ryynanen, A. Klapuri, "Transcription of the singing melody inpolyphonic music", ISMIR 2006.         [ Links ]

[12] F. Ren, D. B. Bracewell, "Advanced information retrieval," JournalElectronic Notes in Theoretical Computer Science (ENTCS) 225, 2009,p. 303-317.         [ Links ]

[13] K. Dressier, "Audio melody extraction", late breaking at ISMIR 2010, Proceedings International Society for Music Information Retrieval Conference (ISMIR 2010), Utrecht, Netherlands, 2010.         [ Links ]

[14] P. V. Kranenburg, J. Garbers, A. Volk, F. Wiering, L. P. Grijp, R. C. Veltkamp, "Collaboration perspectives for folk song research and music information retrieval: The indispensable role of computational musicology," Journal of Interdisciplinary Music Studies, 4 (1), 2010, p. 17-43.         [ Links ]

[15] J. Salamon, E. Gómez, "Melody extraction from polyphonic music audio," Music Information Retrieval Evaluation eXchange (MIREX), Utrecht, The Netherlands, 2010.         [ Links ]

[16] J. Salamon, E. Gómez, "Melody Extraction from Polyphonic Music: MIREX 2011", in Music Information Retrieval Evaluation eXchange (MIREX) 2011, extended abstract, Miami, USA, 2011.         [ Links ]

[17] J. Salamon, E. Gómez, "Melody Extraction from Polyphonic Music Signals using Pitch Contour Characteristics," IEEE Transactions on Audio, Speech and Language Processing, 20(6), 2012, p. 1759-1770.         [ Links ]

[18] A. Ghias, "Query By Humming-Musical Information Retrieval in an Audio Database," Proc. of ACM Multimedia 95, 1995, p 231-236.         [ Links ]

[19] S. Blackburn, D. De Roure, "A Tool for Content Based Navigation of Music,"Proc. ACMMultimedia 98, 1998, p. 361-368.         [ Links ]

[20] R. J. McNab, "Towards the Digital Music Library: Tune Retrieval from Acoustic Input,"Proc. of Digital Libraries, 1996, p. 11-18.         [ Links ]

[21] A. L. P. Chen, M. Chang, J. Chen, "Query by Music Segments: An Efficient Approach for Song Retrieval," Proc. of IEEE International Conference on Multimedia and Expo, 2000.         [ Links ]

[22] C. Francu and C.G Nevill-Manning, "Distance metrics and indexing strategies for a digital library of popular music." 2000 IEEE International Conference on Multimedia and Expo, 2000, ICME 2000, Vol. 2, IEEE, 2000, p. 889-892.         [ Links ]

[23] N.C. Maddage, H. Li, and M.S. Kankanhalli, "Music structure based vector space retrieval," Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval, ACM, 2006, p. 67-74.         [ Links ]

[24] N. Kosugi, Y. Nishihara, S. Kon'ya, M. Yamamuro, and K. Kushima, "Music retrieval by humming-using similarity retrieval over high dimensional feature vector space," 1999 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, IEEE, 1999, p. 404-407.         [ Links ]

[25] L. Chen and B.G Hu, "An implementation of web based query by humming system. 2007 IEEE International Conference on Multimedia and Expo, IEEE, 2007, p. 1467-1470.         [ Links ]

[26] L. Lu, H. You, and H.J. Zhang, "A new approach to query by humming in music retrieval," Proceedings of the IEEE International Conference on Multimedia and Expo, 2001.         [ Links ]

[27] G. Dzhambazov, "Comparisong: Audio comparison engine,"International Book Series Number 11, 2009, p 33.         [ Links ]

[28] M. A. Casey, R. Veltkamp, M. Goto, M. Leman, C. Rhodes, andM. Slaney, "Content-based music information retrieval: current directions and future challenges," Proceedings of the IEEE, 96(4),2008, p. 668-696.         [ Links ]

[30] Soundhound. http://www.soundhound.com.

[31] Musipedia. musipedia. URL: http://www.musipedia.org/.

[32] A. Weibel, T. Hanazawa, G. Hinton, K. Shikano and K. Lang,"Phenomena Recognition Using Time-delay Neural Networks," IEEE Transactions on Acoustics, Speech, and Signal Processing, 37(3),1989, 328-339.         [ Links ]

[33] J. B. Hampshire & A. H. Waibel, "A Novel Objetive Function for Improved Phoneme Recognition Using Time-Delay Neural Networks," IEEE Transactions on Neural Networks, 1, 1990, p. 216-228.         [ Links ]

[34] K. Lang and G Hinton, "A Time-Delay Neural Network Arquitectura for Speech Recognition," Carnegie Mellon University, Tech. Reprt. CMU-CS-88-152, 1988.         [ Links ]

[35] T. Masters, "Advanced Algorithms for Neural Network: A C++ Sourcebook," John Wiley & Sons Inc, 1995.         [ Links ]