Classification of Musical Genres Utilizing the CNN Sequential Model and Deep Learning Techniques
Muskan Singla, Kanwarpartap Singh Gill, Mukesh Kumar, Ruchira Rawat · 2024
In order to categorise musical genres, this study investigates the use of convolutional neural networks (CNN) inside a sequential model framework. This work seeks to improve the precision and effectiveness of automated music genre categorization systems by harnessing the capabilities of deep learning methods. The model under consideration employs a methodology that involves the processing of unprocessed audio data. This procedure entails the extraction of pertinent innovative features by use of convolutional layers, which are designed to capture hierarchical patterns that are intrinsic to certain genres. The use of a sequential architecture in machine learning enables the acquisition of temporal relationships, hence enabling the model to recognise intricate subtleties and variations present in musical compositions. The study access a heterogeneous dataset including many genres in order to enhance the resilience and versatility of the model. This study aims to validate the efficacy of the CNN Sequential Model in properly classifying musical genres. By using rigorous experimentation and assessment, the research endeavours to make a significant contribution to the progress of automated music analysis and classification systems. The results of this study have significant implications for a range of applications, such as music recommendation systems, content tagging, and music streaming services.