On the effectiveness of self-supervised pre-trained models for Persian traditional music information retrieval
Bagher BabaAli, Pouya Mohseni · EURASIP Journal on Audio Speech and Music Processing · 2026
Despite extensive research in music information processing and retrieval, particularly in the context of Western music, there is a notable lack of focus on the processing and retrieval of Persian traditional music. This study stands as the first to examine the effectiveness of self-supervised pre-trained models across various tasks related to Persian traditional music retrieval. Nava dataset, which is a comprehensive collection of Persian traditional musical solos, is utilized for instrument classification, Dastgah recognition, and artist identification. Three pre-trained models, Music2vec, MusicHuBERT, and MERT, are applied and compared across the three tasks. The results indicate that MERT outperforms the other two models across all tasks. Furthermore, the study explores the music signal duration and model fusion on the performance of each task. The findings demonstrate that using combined representations at different levels of layers and model fusion techniques can remarkably improve accuracy. Finally, fine-tuning the pre-trained models results in further enhancements, achieving state-of-the-art accuracy rates of 99.64% for instrument classification, 24.70% for Dastgah recognition, and 79.25% for artist identification on the Nava dataset. • Presenting the first well-organized, comprehensive research on Persian traditional music information retrieval, conducted on a dataset that is extensive in volume, diverse in content, and inclusive of a wide range of instruments and artists. • Provides a comprehensive survey of existing research on traditional Iranian music processing and retrieval. • Examining the effectiveness of self-supervised pre-trained models across various tasks related to Persian traditional music retrieval. • Exploring the effectiveness of various techniques such as model fusion, three levels of representation, and fine-tuning across three targeted tasks. • Achieving state-of-the-art performance in Persian traditional music information retrieval across three tasks. • Offering promising directions for future research and practical applications in Persian traditional music information retrieval.