Abstract
Query-by-humming (QBH) systems take human humming audio as input, and use it as a query to retrieve music from a database as accurately as possible. We propose a novel way of query reformulation for QBH search engine by modeling the user’s humming habits. Query reformulation technologies have been proven to be very effective in many researches. A critical challenge faced by QBH is that the humming is quite inaccurate. Detailed statistics and analysis on a huge number of humming queries and targets has been done based on the IOACAS dataset. Then we summarized the common humming errors that lead to the poor retrieval effect. We defined a five-tuple to represent errors and proposed a user-humming-model based on Hidden Markov model. The query of user is reformulated by the model. The approach is evaluated on Ict- Muse QBH system, SOSO QBH system and midomi QBH system using the QBSH dataset. The experimental results clearly demonstrate that the approach adopted in this paper can greatly improve the quality of the user humming, which in turn improves the effect of information retrieval.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Holmqvist, M., Ciaramita, M., Mahler, D.: Generalized Syntactic and Semantic Models of Query Reformulation. In: ACM SIGIR 2010, pp. 283–290 (2010)
Riezler, S., Liu, Y., Vasserman, A.: Translating queries into snippets for improved query expansion. In: COLING, pp. 737–744 (2008)
Zhang, Z., Nasraoui, O.: Mining search engine query logs for query recommendation. In: ACM WWW, pp. 1039–1040 (2006)
Xu, Y., Gareth, J.F., Jones, B.: Query Dependent Pseudo-Relevance Feedback based on Wikipedia. In: ACM SIGIR 2009 (2009)
Ghias, A., Logan, J., Chamberlin, D., Smith, B.C.: Query by humming: musical information retrieval in an audio database. In: ACM Multimedia Conferenece 1995 (1995)
Ryynanen, M., KJapuri, A.: Query by humming of MIDI and audio using locality sensitive hashing. In: ICASSP 2008, pp. 2249–2252 (2008)
Serra, J., Kantz, H., Serra, X., Andrzejak, R.G.: Predictability of music descriptor time series and its application to cover song detection. IEEE Transaction on Audio, Speech and Language Processing 20(2), 514–525 (2012)
Salamon, J., Gomez, E.: Melody extraction from polyphonic music signals using pitch contour characteristics. IEEE Transaction on Audio, Speech and Language Processing (2012)
Ravuri, S., Ellis, D.: Cover song detection: From high scores to general classification. In: IEEE ICASSP 2010, pp. 65–68 (2010)
Rho, S., Han, B., Hwang, E., Minkoo, K.: MUSEMBLE: A novel music retrieval system with automatic voice query transcription and reformulation. The Journal of Systems and Software 81, 1065–1080 (2008)
Little, D., Raffensperger, D., Pardo, B.: A query by humming system that learns from experience. In: ICMIR (2007)
Meek, C., Birmingham, W.: Johnny Can’t Sing: A Comprehensive Error Model for Sung Music Queries. In: IRCAM 2002, pp.124–132 (2002)
Unal, E., Narayanan, S.S., Shih, H.-H., Chew, E., Kuo, C.C.J.: Creating data resources for designing user-centric frontends for Query by Humming systems. In: ACM Multimedia Information Retrieval Conference 2003 (2003)
Gouyon, F., Dixon, S.: A review of automatic rhythm description systems. Computer Music Journal 29(1), 34–54 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Zhang, G., Lu, K., Wang, B. (2012). Query Reformulation Based on User Habits for Query-by-Humming Systems. In: Hou, Y., Nie, JY., Sun, L., Wang, B., Zhang, P. (eds) Information Retrieval Technology. AIRS 2012. Lecture Notes in Computer Science, vol 7675. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35341-3_34
Download citation
DOI: https://doi.org/10.1007/978-3-642-35341-3_34
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35340-6
Online ISBN: 978-3-642-35341-3
eBook Packages: Computer ScienceComputer Science (R0)