Abstract
Rapid progress in hardware and software technologies has made it possible to manage and access large volumes of music data. The effectiveness (high-accuracy) and efficiency (high-speed) of retrieval techniques for music information data are key issues in the area of large-scale MIR systems. Retrieval performances by conventional methods, however, have not been good enough in large-scale music information retrieval systems. DP matching generally has high retrieval accuracy. However, its retrieval time depends on the size of the database. Thus, to improve the effectiveness and efficiency of music information retrieval in large-scale music databases, two techniques propose: fuzzy-quantization based on melody representation and error-tolerant linear matching. The fuzzy-quantization method uses membership functions based on a probability distribution. The error-tolerant linear matching method is a linear-matching method that considers the possibility of the insertion or omission of notes. Using these techniques, higher recall rates were achieved compared to conventional methods. Retrieval time in pre-selection was about 0.5 seconds per query in large-scale DB, including database loading.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Feng, D., Siu, W.C., Zhang, H.: Multimedia Information Retrieval and Management: Technological Fundamentals and Applications. Springer, Heidelberg (2003)
Coden, A.R., Brown, E.W., Srinivasan, S. (eds.): SIGIR-WS 2001. LNCS, vol. 2273. Springer, Heidelberg (2002)
Heo, S.-P., et al.: Multiple Pitch Candidates based Music Information Retrieval Method for Query-by-Humming. In: International Workshop on AMR 2003, pp. 189–200 (2003)
Zadeh, L.A.: Fuzzy sets. Information and Control 8, 338–353 (1965)
Rabiner, L.R., Juang, B.H.: Fundamentals of Speech Recognition. Prentice-Hall, Englewood Cliffs (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Heo, SP. (2004). Effective and Efficient Melody-Matching Method in a Large-Scale Music Database. In: Meersman, R., Tari, Z., Corsaro, A. (eds) On the Move to Meaningful Internet Systems 2004: OTM 2004 Workshops. OTM 2004. Lecture Notes in Computer Science, vol 3292. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30470-8_15
Download citation
DOI: https://doi.org/10.1007/978-3-540-30470-8_15
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23664-1
Online ISBN: 978-3-540-30470-8
eBook Packages: Springer Book Archive