Classification of Interpretation Differences in String Quartets
Based on the Origin of Performers

J 2023

Classification of Interpretation Differences in String Quartets Based on the Origin of Performers

SPURNÝ, Lubomír, Matěj IŠTVÁNEK and Štěpán MIKLÁNEK

Basic information

Original name

Classification of Interpretation Differences in String Quartets Based on the Origin of Performers

Authors

SPURNÝ, Lubomír (203 Czech Republic, guarantor, belonging to the institution), Matěj IŠTVÁNEK (203 Czech Republic) and Štěpán MIKLÁNEK (203 Czech Republic)

Edition

Applied Sciences-Basel, BASEL, MDPI AG, 2023, 2076-3417

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

20202 Communication engineering and systems

Country of publisher

Switzerland

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

Web výsledku

Impact factor

Impact factor: 2.700 in 2022

RIV identification code

RIV/00216224:14210/23:00134454

Organization unit

Faculty of Arts

DOI

http://dx.doi.org/10.3390/app13063603

UT WoS

000957406100001

Keywords (in Czech)

česká hudba; smyčcový kvartet; analýza interpretačního výkonu; získávání informací; automatické učení; software

Keywords in English

Czech music; string quartet; music analysis; classification; interpretation; machine learning; music information retrieval; origin; synchronization

Abstract

V originále

Music Information Retrieval aims at extracting relevant features from music material, while Music Performance Analysis uses these features to perform semi-automated music analysis. Examples of interdisciplinary cooperation are, for example, various classification tasks—from recognizing specific performances, musical structures, and composers to identifying music genres. However, some classification problems have not been addressed yet. In this paper, we focus on classifying string quartet music interpretations based on the origin of performers. Our dataset consists of string quartets from composers A. Dvořák, L. Janáček, and B. Smetana. After transferring timing information from reference recordings to all target recordings, we apply feature selection methods to rank the significance of features. As the main contribution, we show that there are indeed origin-based tempo differences, distinguishable by measure durations, by which performances may be identified. Furthermore, we train a machine learning classifier to predict the performers’ origin. We evaluate three different experimental scenarios and achieve higher classification accuracy compared to the baseline using synchronized measure positions.

Links

TL05000527, research and development project

Name: Paměť zvuku: evoluční principy interpretační tradice české hudby na příkladu děl Antonína Dvořáka a Bedřicha Smetany

Investor: Technology Agency of the Czech Republic

Citovat

SPURNÝ, Lubomír, Matěj IŠTVÁNEK and Štěpán MIKLÁNEK. Classification of Interpretation Differences in String Quartets Based on the Origin of Performers. Applied Sciences-Basel. BASEL: MDPI AG, 2023, vol. 13, No 6, p. 1-20. ISSN 2076-3417. Available from: https://dx.doi.org/10.3390/app13063603.

@article{2268037,
   author = {Spurný, Lubomír and Ištvánek, Matěj and Miklánek, Štěpán},
   article_location = {BASEL},
   article_number = {6},
   doi = {http://dx.doi.org/10.3390/app13063603},
   keywords = {Czech music; string quartet; music analysis; classification; interpretation; machine learning; music information retrieval; origin; synchronization},
   language = {eng},
   issn = {2076-3417},
   journal = {Applied Sciences-Basel},
   title = {Classification of Interpretation Differences in String Quartets Based on the Origin of Performers},
   url = {https://www.mdpi.com/2076-3417/13/6/3603},
   volume = {13},
   year = {2023}
}

TY  - JOUR
ID  - 2268037
AU  - Spurný, Lubomír - Ištvánek, Matěj - Miklánek, Štěpán
PY  - 2023
TI  - Classification of Interpretation Differences in String Quartets Based on the Origin of Performers
JF  - Applied Sciences-Basel
VL  - 13
IS  - 6
SP  - 1-20
EP  - 1-20
PB  - MDPI AG
SN  - 20763417
KW  - Czech music
KW  - string quartet
KW  - music analysis
KW  - classification
KW  - interpretation
KW  - machine learning
KW  - music information retrieval
KW  - origin
KW  - synchronization
UR  - https://www.mdpi.com/2076-3417/13/6/3603
N2  - Music Information Retrieval aims at extracting relevant features from music material, while Music Performance Analysis uses these features to perform semi-automated music analysis. Examples of interdisciplinary cooperation are, for example, various classification tasks—from recognizing specific performances, musical structures, and composers to identifying music genres. However, some classification problems have not been addressed yet. In this paper, we focus on classifying string quartet music interpretations based on the origin of performers. Our dataset consists of string quartets from composers A. Dvořák, L. Janáček, and B. Smetana. After transferring timing information from reference recordings to all target recordings, we apply feature selection methods to rank the significance of features. As the main contribution, we show that there are indeed origin-based tempo differences, distinguishable by measure durations, by which performances may be identified. Furthermore, we train a machine learning classifier to predict the performers’ origin. We evaluate three different experimental scenarios and achieve higher classification accuracy compared to the baseline using synchronized measure positions.
ER  -

SPURNÝ, Lubomír, Matěj IŠTVÁNEK and Štěpán MIKLÁNEK. Classification of Interpretation Differences in String Quartets Based on the Origin of Performers. \textit{Applied Sciences-Basel}. BASEL: MDPI AG, 2023, vol.~13, No~6, p.~1-20. ISSN~2076-3417. Available from: https://dx.doi.org/10.3390/app13063603.

Detailed Information on Publication Record