Music Structure Analysis and Its Application to Theme Phrase Extraction

  • Atsuhiro Takasu
  • Takashi Yanase
  • Teruhito Kanazawa
  • Jun Adachi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1696)

Abstract

Music is an important component of digital libraries. This paper discusses a digital music library from the information retrieval viewpoint and proposes a method for extracting theme phrases. These are then used to present a shorter version of retrieved music to users. The method consists of two steps, phrase extraction and syntactical classification of segmented fragments of melodies. Phrase extraction is carried out based on a few heuristic rules. We conducted an experiment on the accuracy of phrase extraction using 94 Japanese popular songs and obtained 0.766 recall and 0.786 precision. The syntactical classification is based on a probabilistic syntactical pattern analysis combining classification and syntactical analysis. The proposed method uses a decision tree and a finite state automaton and obtained 0.884 accuracy in theme phrase extraction.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    I. V. Bakhmutova, V. D. Gusev, and T. N. Titkova.: The Search for Adaptations in Song Melodies. Computer Music Journal, 21(1):58–67, 1997.CrossRefGoogle Scholar
  2. 2.
    L. E. Baum.: An Inequality and Associated Maximization Technique in Statistical Estimation for Probabilistic Functions of a markov Process. Inequalities, 3:1–8, 1972.Google Scholar
  3. 3.
    V. Gaede and O. Günter.: Multidimensional Access Methods. Technical report, Humboldt-Universität zu Berlin, 1996.Google Scholar
  4. 4.
    A. Ghias, J. Logan, D. Chamberlin, and B. C. Smith.: Query By Humming–Musical Information Retrieval in an Audio Database. In Proc. of ACM Multimedia–95, 1995.Google Scholar
  5. 5.
    M. Goto and Y. Muraoka.: An Audio-based Real-time Beat Tracking System and Its Applications. In Proc. of International Computer Music Conference, pages 17–20, 1998.Google Scholar
  6. 6.
    M. Goto and Y. Muraoka.: A WWW-based Music Retreival System. http://www.info.waseda.ac.jp/muraoka/members/sonoda/m-search.html.
  7. 7.
    J. W. Hunt and T. G. Szymanski.: A Fast Algorithm for Computing Longest Common Subsequences. Communications of ACM, 20(5):350–353, 1977.MATHCrossRefMathSciNetGoogle Scholar
  8. 8.
    F. Lerdahl and R Jackendoff: A Generative Theory of Tonal Music. The MIT Press, 1983.Google Scholar
  9. 9.
    S. Y. Lu and K. S. Fu.: Stochastic Error-Correcting Syntax Analysis for Recognition of Noi sy Patterns. IEEE Transactions on Computers, C-26(12):1268–1276, 1977.CrossRefMathSciNetGoogle Scholar
  10. 10.
    M. Masui and T. Kakimoto.: Sensitivity-based Audio Positioning for 3D Browsing Navigator(in Japanese). IPSJ SIG Notes, 26(17):115–122, 1998.Google Scholar
  11. 11.
    D. Michie, D. J. Spiegelhalter, and C.C. Taylor.: Machine Learning, Neural And Statistical Classification. Ellis Horwood, 1994.Google Scholar
  12. 12.
    E. Narmout.: The Analysis and Congnition of Basic Melodic Structure. University of Chicago Press, 1990.Google Scholar
  13. 13.
    J. Ross Quinlan. C4.5: Programs for Machine Learning. Morgan Kaufmann, 1993.Google Scholar
  14. 14.
    Curtise Roads.: The Computer Music Tutorial. The MIT Press, 1996.Google Scholar
  15. 15.
    Robert Rowe.: Interactive music systems: machine listening and composing. The MIT Press, 1993.Google Scholar
  16. 16.
    M. Smith and T. Kanade.: Video Skimming and Characterization through the Combination of Image and Language Understanding. Technical report, CMU School of Computer Science, 1996.Google Scholar
  17. 17.
    Y. Tsuji, M. Hoshi, and T. Ohmori.: Local Patterns of a Melody and Its Applications to Retrieval by Sensitive Words (in Japanese). Technical Report of IEICE, SP96(124):17–24, 1997.Google Scholar
  18. 18.
    T. Yanase, A. Takasu, and J. Adachi.: Phrase Based Feature Extraction for Musical Information Retrieval. to appear in IEEE Pacific Rim Conference on Communications, Computers and Signal Processing (PACRIM’99), 1999.Google Scholar
  19. 19.
    Takashi Yanase.: A Melody Retrieval System by Feature Extraction from Musical Performance Information (in Japanese). Master thesis, Graduate Scool of Engineering, University of Tokyo, 1999.Google Scholar
  20. 20.
    T. Yoshino, H. Takagi, Y. Kiyoki, and T. kitagawa.: An Automatic Metadata Creation Method for Music Data and its Application to Semantic Associative Search (in Japanese). IPSJ SIG Notes, 98(58):109–116, 1998.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Atsuhiro Takasu
    • 1
  • Takashi Yanase
    • 2
  • Teruhito Kanazawa
    • 2
  • Jun Adachi
    • 1
  1. 1.Research & Development DepartmentNational Center for Science Information SystemsJapan
  2. 2.Graduate School of EngineeringUniversity of TokyoJapan

Personalised recommendations