Music Performers Classification by Using Multifractal Features: A Case Study

In this paper, we investigated the possibility to classify different performers playing the same melodies at the same manner being subjectively quite similar and very difficult to distinguish even for musically skilled persons. For resolving this problem we propose the use of multifractal (MF) analy...

Full description

Saved in:
Bibliographic Details
Main Authors: Natasa RELJIN, David POKRAJAC
Format: Article
Language:English
Published: Institute of Fundamental Technological Research Polish Academy of Sciences 2017-04-01
Series:Archives of Acoustics
Subjects:
Online Access:https://acoustics.ippt.pan.pl/index.php/aa/article/view/1642
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849711404562513920
author Natasa RELJIN
David POKRAJAC
author_facet Natasa RELJIN
David POKRAJAC
author_sort Natasa RELJIN
collection DOAJ
description In this paper, we investigated the possibility to classify different performers playing the same melodies at the same manner being subjectively quite similar and very difficult to distinguish even for musically skilled persons. For resolving this problem we propose the use of multifractal (MF) analysis, which is proven as an efficient method for describing and quantifying complex natural structures, phenomena or signals. We found experimentally that parameters associated to some characteristic points within the MF spectrum can be used as music descriptors, thus permitting accurate discrimination of music performers. Our approach is tested on the dataset containing the same songs performed by music group ABBA and by actors in the movie Mamma Mia. As a classifier we used the support vector machines and the classification performance was evaluated by using the four-fold cross-validation. The results of proposed method were compared with those obtained using mel-frequency cepstral coefficients (MFCCs) as descriptors. For the considered two-class problem, the overall accuracy and F-measure higher than 98% are obtained with the MF descriptors, which was considerably better than by using the MFCC descriptors when the best results were less than 77%.
format Article
id doaj-art-376069e5965249e1a977458ac60c197c
institution DOAJ
issn 0137-5075
2300-262X
language English
publishDate 2017-04-01
publisher Institute of Fundamental Technological Research Polish Academy of Sciences
record_format Article
series Archives of Acoustics
spelling doaj-art-376069e5965249e1a977458ac60c197c2025-08-20T03:14:38ZengInstitute of Fundamental Technological Research Polish Academy of SciencesArchives of Acoustics0137-50752300-262X2017-04-0142210.1515/aoa-2017-0025Music Performers Classification by Using Multifractal Features: A Case StudyNatasa RELJIN0David POKRAJAC1University of ConnecticutDelaware State UniversityIn this paper, we investigated the possibility to classify different performers playing the same melodies at the same manner being subjectively quite similar and very difficult to distinguish even for musically skilled persons. For resolving this problem we propose the use of multifractal (MF) analysis, which is proven as an efficient method for describing and quantifying complex natural structures, phenomena or signals. We found experimentally that parameters associated to some characteristic points within the MF spectrum can be used as music descriptors, thus permitting accurate discrimination of music performers. Our approach is tested on the dataset containing the same songs performed by music group ABBA and by actors in the movie Mamma Mia. As a classifier we used the support vector machines and the classification performance was evaluated by using the four-fold cross-validation. The results of proposed method were compared with those obtained using mel-frequency cepstral coefficients (MFCCs) as descriptors. For the considered two-class problem, the overall accuracy and F-measure higher than 98% are obtained with the MF descriptors, which was considerably better than by using the MFCC descriptors when the best results were less than 77%.https://acoustics.ippt.pan.pl/index.php/aa/article/view/1642music classificationmultifractal analysissupport vector machinescross-validationmel-frequency cepstral coefficients
spellingShingle Natasa RELJIN
David POKRAJAC
Music Performers Classification by Using Multifractal Features: A Case Study
Archives of Acoustics
music classification
multifractal analysis
support vector machines
cross-validation
mel-frequency cepstral coefficients
title Music Performers Classification by Using Multifractal Features: A Case Study
title_full Music Performers Classification by Using Multifractal Features: A Case Study
title_fullStr Music Performers Classification by Using Multifractal Features: A Case Study
title_full_unstemmed Music Performers Classification by Using Multifractal Features: A Case Study
title_short Music Performers Classification by Using Multifractal Features: A Case Study
title_sort music performers classification by using multifractal features a case study
topic music classification
multifractal analysis
support vector machines
cross-validation
mel-frequency cepstral coefficients
url https://acoustics.ippt.pan.pl/index.php/aa/article/view/1642
work_keys_str_mv AT natasareljin musicperformersclassificationbyusingmultifractalfeaturesacasestudy
AT davidpokrajac musicperformersclassificationbyusingmultifractalfeaturesacasestudy