Publication result detail

Music Information Retrieval Techniques for Determining the Place of Origin of a Music Interpretation

KISKA, T.; GALÁŽ, Z.; ZVONČÁK, V.; MUCHA, J.; MEKYSKA, J.; SMÉKAL, Z.

Original Title

Music Information Retrieval Techniques for Determining the Place of Origin of a Music Interpretation

English Title

Music Information Retrieval Techniques for Determining the Place of Origin of a Music Interpretation

Type

Paper in proceedings (conference paper)

Original Abstract

Determining the place of origin of musical compositions is a modern area of research in the field of music information retrieval (MIR). A musical interpretation of one piece carries a variety of author’s intentions that influence the musical character of resulting composition. These aspects may include rhythm, dynamics, timbre, or tonality. This paper introduces a novel methodology for determining the place of origin of a music interpretation based on advanced signal processing and machine learning techniques. For this purpose, we collected a database of 35 different interpretations of Leos Janacek’s String Quartet No. 1, “Kreutzer Sonata”: IV. Con Moto – Adagio. Employing random forests classifier, we achieved classification accuracy over 97 % using features derived from Mel-frequency cepstral coefficients. This paper proves it is possible to use MIR for determining the origin of a music interpretation with very high accuracy.

English abstract

Determining the place of origin of musical compositions is a modern area of research in the field of music information retrieval (MIR). A musical interpretation of one piece carries a variety of author’s intentions that influence the musical character of resulting composition. These aspects may include rhythm, dynamics, timbre, or tonality. This paper introduces a novel methodology for determining the place of origin of a music interpretation based on advanced signal processing and machine learning techniques. For this purpose, we collected a database of 35 different interpretations of Leos Janacek’s String Quartet No. 1, “Kreutzer Sonata”: IV. Con Moto – Adagio. Employing random forests classifier, we achieved classification accuracy over 97 % using features derived from Mel-frequency cepstral coefficients. This paper proves it is possible to use MIR for determining the origin of a music interpretation with very high accuracy.

Keywords

music analysis; musical features; feature calculation; music synchronization; dynamic time warping; audio-to-audio alignment; music information retrieval.

Key words in English

music analysis; musical features; feature calculation; music synchronization; dynamic time warping; audio-to-audio alignment; music information retrieval.

Authors

KISKA, T.; GALÁŽ, Z.; ZVONČÁK, V.; MUCHA, J.; MEKYSKA, J.; SMÉKAL, Z.

RIV year

2019

Released

05.11.2018

Location

Moskva, Rusko

ISBN

978-1-5386-9360-5

Book

10th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)

Pages from

238

Pages to

242

Pages count

5

BibTex

@inproceedings{BUT149606,
  author="KISKA, T. and GALÁŽ, Z. and ZVONČÁK, V. and MUCHA, J. and MEKYSKA, J. and SMÉKAL, Z.",
  title="Music Information Retrieval Techniques for Determining the Place of Origin of a Music Interpretation",
  booktitle="10th International Congress on Ultra Modern Telecommunications and Control Systems and Workshops (ICUMT)",
  year="2018",
  pages="238--242",
  address="Moskva, Rusko",
  doi="10.1109/ICUMT.2018.8631268",
  isbn="978-1-5386-9360-5"
}