Comparative Analysis of Different Performances in Digital Music Recordings Using Information Theory Metrics and Audio Features
International Journal of Advances in Engineering and Pure Sciences · 30.06.2026 · 38 (2) · 386-403
DOI: 10.7240/jeps.1888024 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Advances in Engineering and Pure Sciences, online erschienen am 30.06.2026. Verfasst von Ali Özhan Akyüz und 2 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben.
Abstract (Originalsprache)
This study presents a comparative analysis of different performances of the same musical work using information theory metrics and audio features. The research utilizes MP3 recordings of seven distinct musical works. These recordings include: different orchestral interpretations of the same piece, vocal performances by different artists (including both female and male singers), and versions of the same work performed by one female and one male artist. During the analysis, both the full recordings and the initial 30-second segments of each work were evaluated. For each audio file, the following analyses were performed: waveform visualization, spectrogram, power spectral density (PSD), and Mel-Frequency Cepstral Coefficients (MFCCs). Information theory metrics calculated include: Shannon entropy, perplexity, Kullback-Leibler (KL) divergence, joint entropy, cross entropy, conditional entropy, and mutual information. Additionally, t-test p-values for audio features such as MFCCs and spectral centroid were obtained. Through within-group and between-group comparisons, the effects of orchestra, artist, and gender differences on these metrics were investigated. The results demonstrate that differences in musical interpretation create statistically measurable effects on both information theory metrics and audio features.
Zitieren
APA
Akyüz, A. Ö., Pençe, İ., & Yıldırım, R. (2026). Comparative Analysis of Different Performances in Digital Music Recordings Using Information Theory Metrics and Audio Features. International Journal of Advances in Engineering and Pure Sciences, 38(2), 386-403. https://doi.org/10.7240/jeps.1888024
Vancouver
Akyüz AÖ, Pençe İ, Yıldırım R. Comparative Analysis of Different Performances in Digital Music Recordings Using Information Theory Metrics and Audio Features. International Journal of Advances in Engineering and Pure Sciences. 2026;38(2):386-403. doi:10.7240/jeps.1888024
BibTeX
@article{Akyz2026,
author = {Akyüz, Ali Özhan and Pençe, İhsan and Yıldırım, Ragıp},
title = {Comparative Analysis of Different Performances in Digital Music Recordings Using Information Theory Metrics and Audio Features},
journal = {International Journal of Advances in Engineering and Pure Sciences},
year = {2026},
volume = {38},
number = {2},
pages = {386--403},
doi = {10.7240/jeps.1888024}
}
EUVIMED