Instrument-Independent Dastgah Recognition of Iranian Classical Music Using AzarNet

TL;DR

This paper introduces AzarNet, a deep neural network that achieves state-of-the-art accuracy in recognizing seven Dastgahs of Iranian classical music using spectrogram features from audio signals.

Contribution

The paper presents a novel deep neural network architecture, AzarNet, specifically designed for Dastgah recognition, achieving the highest reported accuracy on the MICM dataset.

Findings

AzarNet achieved an 86.21% F1 score on test data.

The approach outperforms previous methods in Dastgah classification.

Spectrogram features from STFT effectively support deep learning models for music classification.

Abstract

In this paper, AzarNet, a deep neural network (DNN), is proposed to recognizing seven different Dastgahs of Iranian classical music in Maryam Iranian classical music (MICM) dataset. Over the last years, there has been remarkable interest in employing feature learning and DNNs which lead to decreasing the required engineering effort. DNNs have shown better performance in many classification tasks such as audio signal classification compares to shallow processing architectures. Despite image data, audio data need some preprocessing steps to extract spectra and temporal features. Some transformations like Short-Time Fourier Transform (STFT) have been used in the state of art researches to transform audio signals from time-domain to time-frequency domain to extract both temporal and spectra features. In this research, the STFT output results which are extracted features are given to AzarNet for learning and classification processes. It is worth noting that, the mentioned dataset contains music tracks composed with two instruments (violin and straw). The overall f1 score of AzarNet on test set, for average of all seven classes was 86.21% which is the best result ever reported in Dastgah classification according to our best knowledge.