Abstract
Query-by-Humming (QBH) systems transcribe a sung or hummed query and search for related musical themes in a database, returning the most similar themes as a play list. A major obstacle to effective QBH is variation between user queries and the melodic targets used as database search keys. Since it is not possible to predict all individual singer profiles before system deployment, a robust QBH system should be able to adapt to different singers after deployment. Currently deployed systems do not have this capability. We describe a new QBH system that learns from user provided feedback on the search results, letting the system improve while deployed, after only a few queries. This is made possible by a trainable note segmentation system, an easily parameterized singer error model and a straight-forward genetic algorithm. Results show significant improvement in performance given only ten example queries from a particular user.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Dannenberg, R., Birmingham, W., Pardo, B., Hu, N., Meek, C., Tzanetakis, G.: A comparative evaluation of search techniques for query-by-humming using the mustart testbed. Journal of the American Society for Information Sicence and Technology 58(3) (2007)
Kosugi, N., Sakurai, Y., Morimoto, M.: Soundcompass: A practical query-by-humming system; normalization of scalable and shiftable time-series data and effective subsequence generation. In: International Conference on Management of Data, Paris, France, pp. 881–886 (2004)
Pauws, S.: Cubyhum: A fully operation query by humming system. In: ISMIR (2002)
Shifrin, J., Pardo, B., Meek, C., Birmingham, W.: Hmm-based musical query retrieval. In: Joint Conference on Digital Libraries, Portland, Oregon, USA (2002)
Unal, E., Narayanan, S., Chew, E.: A statistical approach to retrieval under user-dependent uncertainty in query-by-humming systems. In: Multimedia Information Retrieval Conference, New York (2004)
Meek, C., Birmingham, W.: A comprehensive trainable error model for sung music queries. Journal of Artificial Intelligence Research 22, 57–91 (2004)
Pardo, B., Birmingham, W.P., Shifrin, J.: Name that tune: A pilot study in finding a melody from a sung query. Journal of the American Society for Information Science and Technology 55(4), 283–300 (2004)
Parker, C., Fern, A., Tadepalli, P.: Gradient boosting for sequence alignment. In: The Twenty First National Conference on Artificial Intelligence (2006)
Pardo, B., Shamma, D.: Teaching a music search engine through play. In: CHI 2007. Computer/Human Interaction (2007)
Pardo, B., Birmingham, W.: Encoding timing information for music query matching. In: International Conference on Music Information Retrieval (2002)
Elder, J.H., Zucker, S.W.: Local scale control for edge detection and blur estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence 20(7), 699–716 (1998)
Meer, P., Georgescu, B.: Edge detection with embedded confidence. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(12), 1351–1365 (2001)
Ahmad, M.B., Tae-Sun, C.: Local threshold and boolean function based edge detection. IEEE Transactions on Consumer Electronics 45(3), 674–679 (1999)
Tzanetakis, G., Cook, F.: A framework for audio analysis based on classification and temporal segmentation. In: EUROMICRO Confrence, Milan, vol. 2, pp. 61–67 (1999)
Shepard, R.: Geometrical approximations to the structure of musical pitch. Psychological Review 89(4), 305–309 (1982)
Criani, P.: Temporal codes, timing nets, and music perception. Journal of New Music Research 30(2), 107–135 (2001), Good/useful representation of pitch similarity here, also some interesting ideas on how to use temporal codes throughout computation.
Parker, J.: Genetic algorithms for continuous problems. In: 15th Conference of the Canadian Society for Computational Studies of Intelligence on Advances in Artificial Intelligence (2002)
Wright, A.: Genetic algorithms for real parameter optimization. In: The First workshop on the Foundations of Genetic Algorithms and Classier Systems (1990)
Jyh-Shing, J.R.: Qbsh: A corups for designing qbsh (query by singing/humming) systems, Available at the QBSH corpus for query by singing/humming link at the organizer’s homepage (2006)
Downie, J.S., West, K., Ehmann, A., Vincent, E.: The 2005 music information retrieval evaluation exchange (mirex 2005): Preliminary overview. In: 6th International Conference on Music Information Retrieval (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Little, D., Raffensperger, D., Pardo, B. (2008). User Specific Training of a Music Search Engine. In: Popescu-Belis, A., Renals, S., Bourlard, H. (eds) Machine Learning for Multimodal Interaction. MLMI 2007. Lecture Notes in Computer Science, vol 4892. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-78155-4_7
Download citation
DOI: https://doi.org/10.1007/978-3-540-78155-4_7
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-78154-7
Online ISBN: 978-3-540-78155-4
eBook Packages: Computer ScienceComputer Science (R0)