Enhanced Bengali audio categorization using audio segmentation and deep learning
Abstract
This paper presents an enhanced approach for classifying Bengali songs into different genres by leveraging feature importance analysis and deep learning techniques. The research addresses the challenge of limited data points in the Bengali Song Dataset by employing strategies, including audio segmentation and feature importance analysis, to enhance model performance. Multiple machine learning and deep learning architectures are evaluated to identify the most effective models for Bengali song classification. Additionally, this research conducts feature importance analysis to identify significant audio features contributing to classification accuracy. The best-performing deep learning model achieves an impressive validation accuracy of 94.17%, showcasing the project efficacy of the proposed methodology. Our findings highlight the effectiveness of our proposed methodology, demonstrating significant improvements in classification accuracy and contributing to advancements in Bengali music classification research.
Keywords
Audio signal processing; Augmentation; MFCC; Neural network; Segmentation
Full Text:
PDFDOI: http://doi.org/10.11591/ijeecs.v36.i2.pp952-960
Refbacks
- There are currently no refbacks.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Indonesian Journal of Electrical Engineering and Computer Science (IJEECS)
p-ISSN: 2502-4752, e-ISSN: 2502-4760
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).