A dataset and classification model for Malay, Hindi, Tamil and Chinese music

TL;DR

This paper introduces a new dataset of music from Singapore's main ethnic groups and develops classification models to identify the origin of music based on various musical features.

Contribution

The paper provides a novel dataset and explores multiple feature-based classification models for ethnic music origin identification.

Findings

High accuracy in classifying music by ethnic origin

Effective use of both high-level and low-level musical features

Improved model performance through feature optimization

Abstract

In this paper we present a new dataset, with musical excepts from the three main ethnic groups in Singapore: Chinese, Malay and Indian (both Hindi and Tamil). We use this new dataset to train different classification models to distinguish the origin of the music in terms of these ethnic groups. The classification models were optimized by exploring the use of different musical features as the input. Both high level features, i.e., musically meaningful features, as well as low level features, i.e., spectrogram based features, were extracted from the audio files so as to optimize the performance of the different classification models.