Abstract
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.
Funder
National Key Research and Development Program of China
Publisher
Public Library of Science (PLoS)
Reference53 articles.
1. Music genre classification and music recommendation by using deep learning;A Elbir;Electronics Letters,2020
2. Elbir A, Çam HB, Iyican ME, Öztürk B, Aydin N. Music Genre Classification and Recommendation by Using Machine Learning Techniques. In: 2018 Innovations in Intelligent Systems and Applications Conference (ASYU). IEEE; 2018. p. 1–5.
3. Musical genre classification of audio signals;G Tzanetakis;IEEE Transactions on speech and audio processing,2002
4. Content-based classification, search, and retrieval of audio;E Wold;IEEE multimedia,1996
5. Oral and written transmission in Ethiopian Christian chant;KK Shelemay;Early Music History,1993
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献