YMIR: A new Benchmark Dataset and Model for Arabic Yemeni Music Genre Classification Using Convolutional Neural Networks

Moeen AL-Makhlafi; Abdulrahman A. AlKannad; Eiad Almekhlafi; Nawaf Q. Othman Ahmed Mohammed; Saher Qaid

cs.SDApr 6, 2026

YMIR: A new Benchmark Dataset and Model for Arabic Yemeni Music Genre Classification Using Convolutional Neural Networks

Authors: Moeen AL-Makhlafi, Abdulrahman A. AlKannad, Eiad Almekhlafi, Nawaf Q. Othman Ahmed Mohammed, Saher Qaid

Organizations: School of Artificial Intelligence, Xidian University, Xi’an, China. · Department of Information Science and Technology, Northwest University, Xi’an 710127, China.

Abstract

Automatic music genre classification is a major task in music information retrieval; however, most current benchmarks and models have been developed primarily for Western music, leaving culturally specific traditions underrepresented. In this paper, we introduce the Yemeni Music Information Retrieval (YMIR) dataset, which contains 1,475 carefully selected audio clips covering five traditional Yemeni genres: Sanaani, Hadhrami, Lahji, Tihami, and Adeni. The dataset was labeled by five Yemeni music experts following a clear and structured protocol, resulting in strong inter-annotator agreement (Fleiss kappa = 0.85). We also propose the Yemeni Music Classification Model (YMCM), a convolutional neural network (CNN)-based system designed to classify music genres from time-frequency features. Using a consistent preprocessing pipeline, we perform a systematic comparison across six experimental groups and five different architectures, resulting in a total of 30 experiments. Specifically, we evaluate several feature representations, including Mel-spectrograms, Chroma, FilterBank, and MFCCs with 13, 20, and 40 coefficients, and benchmark YMCM against standard models (AlexNet, VGG16, MobileNet, and a baseline CNN) under the same experimental conditions. The experimental findings reveal that YMCM is the most effective, achieving the highest accuracy of 98.8% with Mel-spectrogram features. The results also provide practical insights into the relationship between feature representation and model capacity. The findings establish YMIR as a useful benchmark and YMCM as a strong baseline for classifying Yemeni music genres.

Figures & tables

Fig. 1: Waveform samples of the five YMIR genre classification dataset.

Fig. 3: Workflow diagram of the proposed framework

Fig. 4: WAV-format audio data Short-Time Fourier Transform Extraction.

Fig. 5: Workflow diagram of the proposed framework

Parameter	Value
Number of Epochs	50
Batch Size	16
Learning Rate	0.0001
Optimizer	Adam
Loss Function	Categorical Crossentropy
Early Stopping Patience	10 epochs

TABLE I: Training Parameters Used in the Experiments

Fig. 6: Summary of the experimental design and configurations conducted in this study.

Fig. 7: Validation accuracy of the proposed YMCM framework using several feature extraction methods.

Fig. 8: Validation loss of the proposed YMCM framework using several feature extraction methods.

Panel of Figure 10 — Fig. 9: Confusion matrices for the proposed YMCM model with different audio feature extraction methods: (a) Filterbanks, (b) chroma features, (c) mel spectrogram, (d) 13 MFCCs, (e) 40 MFCCs, (f) 20 MFCCs. All matrices represent a 5-class classification task.

Model	Feature	Acc.	Prec.	Rec.	F1.
	Extraction	(%)	(%)	(%)	(%)
AlexNet	Chroma	74.66	75.20	74.66	74.64
	FilterBanks	94.77	94.79	94.77	94.76
	Mel-Spectrogram	97.25	97.27	97.25	97.24
	MFCC13	94.83	95.03	94.83	94.84
	MFCC20	96.63	96.76	96.63	96.64

TABLE II: Performance Results of Different Models Using Various Feature Extraction Techniques.

Model	Optimal Feature	Accuracy
AlexNet	MFCC40	97.59%
VGG16	Mel-Spectrogram	95.87%
MobileNet	MFCC13 / MFCC20	93.73%
CNN (Baseline)	Mel-Spectrogram	96.28%
YMCM (Proposed)	Mel-Spectrogram	98.83%

TABLE III: Optimal Feature Extraction Strategy for Each Model

Explore similar work

Mar 16, 2026

Music Genre Classification: A Comparative Analysis of Classical Machine Learning and Deep Learning Approaches

Automatic music genre classification is a long-standing challenge in Music Information Retrieval (MIR); work on non-Western music traditions remains scarce. Nepali music encompasses culturally rich and acoustically diverse genres--from the call-and-response duets of Lok Dohori to the rhythmic poetry of Deuda and the distinctive melodies of Tamang Selo--that have not been addressed by existing classification systems. In this paper, we construct a novel dataset of approximately 8,000 labeled 30-second audio clips spanning eight Nepali music genres and conduct a systematic comparison of nine classification models across two paradigms. Five classical machine learning classifiers (Logistic Regression, SVM, KNN, Random Forest, and XGBoost) are trained on 51 hand-crafted audio features extracted via Librosa, while four deep learning architectures (CNN, RNN, parallel CNN-RNN, and sequential CNN followed by RNN) operate on Mel spectrograms of dimension 640 x 128. Our experiments reveal that the sequential Convolutional Recurrent Neural Network (CRNN)--in which convolutional layers feed into an LSTM--achieves the highest accuracy of 84%, substantially outperforming both the best classical models (Logistic Regression and XGBoost, both at 71%) and all other deep architectures. We provide per-class precision, recall, F1-score, confusion matrices, and ROC analysis for every model, and offer a culturally grounded interpretation of misclassification patterns that reflects genuine overlaps in Nepal's musical traditions.

Sachin Prajuli, Abhishek Karna, OmPrakash Dhakl

Computer Science and Engineering, University of texas at Arlington, Arlington, USA · Electronics and Computer Engineering, Tribhuvan University, IOE, kathmandu · Electronics and Computer Engineering, Tribhuvan University, IOE, Dharan

Audio Classification Music Information Retrieval Convolutional RNNs

Ask PDF

Sep 15, 2026

The Internet Archive Music Dataset

We introduce the Internet Archive Music Dataset (IAMD), a large-scale collection of captioned music segments derived from the Internet Archive. To the best of our knowledge, IAMD constitutes the largest publicly available music-caption dataset to date with over 34,000 hours of audio, providing a valuable benchmark for training and evaluating music understanding and generative models. The dataset is built from content declared to be distributed under Creative Commons licenses, and cross-referencing with MusicBrainz is done to improve license information reliability. To annotate IAMD, we present an automatic captioning pipeline that augments base captions produced by an audio-language model (ALM) with textual metadata sourced from the Internet Archive and imputed metadata obtained using audio classification models. Caption quality is assessed objectively and subjectively, and results indicate that the annotation pipeline is reliable and does not degrade caption quality with scaling.

Paraskevas Stamatiadis, Bernardo V Miranda, Clémentine Berger +3

S2A, LTCI, IDS · LTCI, Télécom Paris, Institut Polytechnique de Paris, France · LTCI, IP Paris, S2A, IDS, IMT +1

Audio Captioning

Ask PDF

Sep 23, 2026

AraGenre 2026: A Hierarchical Definition-Guided Arabic Genre Classification Shared Task

AraGenre is a shared task on hierarchical, definition-guided Arabic genre classification, motivated by the limited availability of annotated data in Arabic and other low-resource languages. Systems assign each Arabic text segment both a broad communicative genre and a fine-grained specific genre. The released training and development sets contain limited, primarily synthetic and controlled examples, whereas the hidden final benchmark contains noisier naturally occurring text spanning Modern Standard Arabic, Classical Arabic, and multiple dialects. Participants received natural-language definitions for 74 previously unseen specific genres, creating a zero-shot label generalisation setting in which systems had to infer class semantics rather than memorise fixed label-feature associations. The task attracted 46 registrations and 373 submissions, with 17 teams completing the final evaluation. Thakaa ranked first with a Hierarchical Macro F1 of 0.7352, followed by HoangPhong (HP) with 0.7169 and NAMAA with 0.7013. The results show strong broad-genre recognition but a substantial gap in fine-grained classification under linguistic and domain variation.

Mo El-Haj, Saad Ezzini, Shadi Abudalfa +3

VinUniversity, Vietnam · Lancaster University, UK · King Fahd University of Petroleum and Minerals, Saudi Arabia +3

Arabic NLP Zero-Shot Text Classification Text Classification Classification Low-Resource Language Processing

Ask PDF