Persian Musical Instruments Classification Using Polyphonic Data Augmentation
This work addresses the limited research on non-Western musical traditions, specifically Persian music, for music information retrieval and generative systems, though it is incremental as it applies existing models with new data and augmentation.
The paper tackled the problem of classifying musical instruments in Persian music, which is understudied, by introducing a new dataset and a culturally informed data augmentation strategy; the result was a method that achieved a ROC-AUC of 0.795 on real-world polyphonic Persian music, outperforming other approaches.
Musical instrument classification is essential for music information retrieval (MIR) and generative music systems. However, research on non-Western traditions, particularly Persian music, remains limited. We address this gap by introducing a new dataset of isolated recordings covering seven traditional Persian instruments, two common but originally non-Persian instruments (i.e., violin, piano), and vocals. We propose a culturally informed data augmentation strategy that generates realistic polyphonic mixtures from monophonic samples. Using the MERT model (Music undERstanding with large-scale self-supervised Training) with a classification head, we evaluate our approach with out-of-distribution data which was obtained by manually labeling segments of traditional songs. On real-world polyphonic Persian music, the proposed method yielded the best ROC-AUC (0.795), highlighting complementary benefits of tonal and temporal coherence. These results demonstrate the effectiveness of culturally grounded augmentation for robust Persian instrument recognition and provide a foundation for culturally inclusive MIR and diverse music generation systems.