Design and Implementation of a Machine Learning Based Hindi Music Emotion Classification System

DOI

10.2991/978-94-6239-678-4_12How to use a DOI?

Keywords

Music Emotion Recognition; Machine Learning; Audio Features; Music Signal Processing

Abstract

Music Emotion Recognition plays an essential part in detecting particular emotion classes in songs by analysing their emotional content. In this study, we design and implement a MER system based on machine learning using acoustic feature analysis on the Hindi Music dataset MER500. Two experiments are conducted using different window and hop size configurations, i.e. 2048 × 1024 and 1024 × 512, to analyse the effect of temporal segmentation on emotion classification performance. From each configuration, a set of relevant audio features, including MFCCs, spectral descriptors, chroma features, energy, and tempo-related attributes, are extracted. These features are then classified using various machine learning algorithms such as Support Vector Machine, Random Forest, K-Nearest Neighbours. The results from the experiment demonstrate that window–hop size selection significantly influences emotion classification accuracy. Among the tested configurations, a balanced time–frequency resolution provides superior performance and computational efficiency. The proposed system offers an effective and scalable solution for Hindi music emotion recognition and highlights the importance of optimised signal processing parameters for improved classification performance.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Akanksha Gupta
AU  - Anamika Singh
PY  - 2026
DA  - 2026/05/28
TI  - Design and Implementation of a Machine Learning Based Hindi Music Emotion Classification System
BT  - Proceedings of the 2nd International Conference on Recent Advancement and Modernization in Sustainable Intelligent Technologies & Applications (RAMSITA-2026)
PB  - Atlantis Press
SP  - 137
EP  - 147
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-678-4_12
DO  - 10.2991/978-94-6239-678-4_12
ID  - Gupta2026
ER  -