• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

A Design of Matching Engine for a Practical Query-by-Singing /Humming System with Polyphonic Recordings

Vol. 8, No.2, February 27, 2014
10.3837/tiis.2014.02.024, Download Paper (Free):

Abstract

This paper proposes a matching engine for a query-by-singing/humming (QbSH) system with polyphonic music files like MP3 files. The pitch sequences extracted from polyphonic recordings may be distorted. So we use chroma-scale representation, pre-processing, compensation, and asymmetric dynamic time warping to reduce the influence of the distortions. From the experiment with 28 hour music DB, the performance of our QbSH system based on polyphonic database is very promising in comparison with the published QbSH system based on monophonic database. It shows 0.725 in MRR(Mean Reciprocal Rank). Our matching engine can be used for the QbSH system based on MIDI DB also and that performance was verified by MIREX 2011.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
Seok-Pil Lee, Hoon Yoo and Dalwon Jang, "A Design of Matching Engine for a Practical Query-by-Singing /Humming System with Polyphonic Recordings," KSII Transactions on Internet and Information Systems, vol. 8, no. 2, pp. 721-734, 2014. DOI: 10.3837/tiis.2014.02.024

[ACM Style]
Lee, S., Yoo, H., and Jang, D. 2014. A Design of Matching Engine for a Practical Query-by-Singing /Humming System with Polyphonic Recordings. KSII Transactions on Internet and Information Systems, 8, 2, (2014), 721-734. DOI: 10.3837/tiis.2014.02.024