Semantic-based Similiarity of Music

Michael Rentzsch, Frank Seifert


Existing approaches to music identification such as audio fingerprinting are generally data-driven and based on statistical information. They require a particular pattern for each individual instance of the same song. Hence, these approaches are not capable of dealing with the vast amount of music that is composed via methods of improvisation and variation. Futhermore, they are unable to measure the similarity of two pieces of music. This paper presents a different, semantic-based view on the identification and structuring of symbolic music patterns. This new method will allow us to detect different instances of the same song and acquire their degree of similarity.


  1. Cano, P., Batlle, E., Kalker T., Haitsma J.: A Review of Algorithms for Audio Fingerprinting. In: International Workshop on Multimedia Signal Processing, US Virgin Islands (2002)
  2. Dowling, W. J.: Scale and contour: Two components of a theory of memory for melodies. In: Psychological Review, p. 341 - 354 (1978)
  3. Haitsma, J., Kalker, T.: A Highly Robust Audio Fingerprinting System. ISMIR, Paris, France (2002)
  4. Neve, G., Orio, N.: Indexing and Retrieval of Music Documents trought Pattern Analysis and Data Fusion Techniques. ISMIR, Barcelona, Spain (2004)
  5. Nishimura, T. et al.: Music Signal Spotting Retrieval by a Humming Query Using Start Frame Feature Dependent Continuous Dynamic Programming. In: Music Information Retrieval, p. 211 - 218, Bloomington, Indiana (2001)
  6. Rentzsch, M.: Entwicklung und Implementierung von Vergleichsoperationen für symbolische Tondokumente, Diploma Thesis. Chemnitz University of Technology, Germany (2005)
  7. Seifert, F.: Musikalische Datenbanken, Dissertation. Chemnitz University of Technology, Germany (2004)
  8. Seifert, F.: Prediction-Driven Correlation of Audio with Generic Music Templates. EuroIMSA, Grindelwald, Switzerland (2005)
  9. Shapiro, L. G., Haralick, R. M.: A metric for comparing relational descriptions. In: IEEE Trans PAMI, p. 90 - 94 (1985)
  10. Song, J., Bae, S. Y., Yoon, K.: Mid-Level Music Melody Representation of Polyphonic Audio for Query-by-Humming System. ISMIR, Paris, France (2002)
  11. Youngmoo, K., Wei C., Ricardo, G., Barry, V.: Analysis of a contour-based representation for melody. Int. Symposium on Music Information Retrieval, Plymouth, Massachusetts (2000)

Paper Citation

in Harvard Style

Rentzsch M. and Seifert F. (2006). Semantic-based Similiarity of Music . In 6th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2006) ISBN 978-972-8865-55-9, pages 175-180. DOI: 10.5220/0002485101750180

in Bibtex Style

author={Michael Rentzsch and Frank Seifert},
title={Semantic-based Similiarity of Music},
booktitle={6th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2006)},

in EndNote Style

JO - 6th International Workshop on Pattern Recognition in Information Systems - Volume 1: PRIS, (ICEIS 2006)
TI - Semantic-based Similiarity of Music
SN - 978-972-8865-55-9
AU - Rentzsch M.
AU - Seifert F.
PY - 2006
SP - 175
EP - 180
DO - 10.5220/0002485101750180