Kiñit classification in Ethiopian chants, Azmaris and modern music: A new dataset and CNN benchmark
PLOS ONE · 2023
DOI: 10.1371/journal.pone.0284560 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS ONE, 2023. Verfasst von Ephrem Afele Retta und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Technology, Northwest University, Xi'an, China. Hauptthemen laut MEDLINE: Music, Singing. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China.
Abstract (Originalsprache)
In this paper, we create EMIR, the first-ever Music Information Retrieval dataset for Ethiopian music. EMIR is freely available for research purposes and contains 600 sample recordings of Orthodox Tewahedo chants, traditional Azmari songs and contemporary Ethiopian secular music. Each sample is classified by five expert judges into one of four well-known Ethiopian Kiñits, Tizita, Bati, Ambassel and Anchihoye. Each Kiñit uses its own pentatonic scale and also has its own stylistic characteristics. Thus, Kiñit classification needs to combine scale identification with genre recognition. After describing the dataset, we present the Ethio Kiñits Model (EKM), based on VGG, for classifying the EMIR clips. In Experiment 1, we investigated whether Filterbank, Mel-spectrogram, Chroma, or Mel-frequency Cepstral coefficient (MFCC) features work best for Kiñit classification using EKM. MFCC was found to be superior and was therefore adopted for Experiment 2, where the performance of EKM models using MFCC was compared using three different audio sample lengths. 3s length gave the best results. In Experiment 3, EKM and four existing models were compared on the EMIR dataset: AlexNet, ResNet50, VGG16 and LSTM. EKM was found to have the best accuracy (95.00%) as well as the fastest training time. However, the performance of VGG16 (93.00%) was found not to be significantly worse ( P < 0.01). We hope this work will encourage others to explore Ethiopian music and to experiment with other models for Kiñit classification.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Information Science and Technology, Northwest University, Xi'an, China.
- School of Computer Science and Electronic Engineering, University of Essex, Colchester, United Kingdom.
- School of Telecommunications Engineering, Xidian University, Xi'an, China.
- School of Computer Science and Technology, Xidian University, Xi'an, China.
- School of Information and Civil Engineering, Chang'an University, Xi'an, China.
- School of Information Science and Technology, Chang'an University, Xi'an, China.
ORCID-Profile: Richard Sutcliffe
Förderung
- National Key Research and Development Program of China
Zitieren
APA
Retta, E. A., Sutcliffe, R., Almekhlafi, E., Enku, Y. K., Alemu, E., Gemechu, T. D., Berwo, M. A., Mhamed, M., & Feng, J. (2023). Kiñit classification in Ethiopian chants, Azmaris and modern music: A new dataset and CNN benchmark. PLOS ONE. https://doi.org/10.1371/journal.pone.0284560
Vancouver
Retta EA, Sutcliffe R, Almekhlafi E, Enku YK, Alemu E, Gemechu TD, et al. Kiñit classification in Ethiopian chants, Azmaris and modern music: A new dataset and CNN benchmark. PLOS ONE. 2023. doi:10.1371/journal.pone.0284560
BibTeX
@article{Retta2023,
author = {Retta, Ephrem Afele and Sutcliffe, Richard and Almekhlafi, Eiad and Enku, Yosef Kefyalew and Alemu, Eyob and Gemechu, Tigist Demssice and Berwo, Michael Abebe and Mhamed, Mustafa and Feng, Jun},
title = {Kiñit classification in Ethiopian chants, Azmaris and modern music: A new dataset and CNN benchmark},
journal = {PLOS ONE},
year = {2023},
doi = {10.1371/journal.pone.0284560}
}
EUVIMED