Automatic Fado Music Classification

TL;DR

This paper presents an automatic Fado music classification system that analyzes audio signals using spectral features, achieving high accuracy and demonstrating Fado's distinctive musical characteristics.

Contribution

The study introduces a novel audio feature set for Fado detection and validates its effectiveness with high accuracy in cross-validation and train/test setups.

Findings

97.6% accuracy in 10-fold cross-validation

95.8% accuracy in train/test setup

Fado's distinctive spectral features enable effective classification

Abstract

In late 2011, Fado was elevated to the oral and intangible heritage of humanity by UNESCO. This study aims to develop a tool for automatic detection of Fado music based on the audio signal. To do this, frequency spectrum-related characteristics were captured form the audio signal: in addition to the Mel Frequency Cepstral Coefficients (MFCCs) and the energy of the signal, the signal was further analysed in two frequency ranges, providing additional information. Tests were run both in a 10-fold cross-validation setup (97.6% accuracy), and in a traditional train/test setup (95.8% accuracy). The good results reflect the fact that Fado is a very distinctive musical style.