<![CDATA[This study articulates a deep learning approach for classifying Carnatic and Non-Carnaticmusic using Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN). Thedifferential features, such as microtones, and improvisational structures of Carnatic music causesevere difficulties in the application of automated genre classification. Thus, audio features ofMFCCs, chroma features, and spectrograms were extracted to capture key spectral and tonalproperties in order to realize excellent classification. The CNN model achieved an accuracy of 95.1%,outperforming the RNN model's 93.8%, with ROC-AUC scores of 0.96 and 0.94, respectively. Thesemetrics indicate the CNN’s effectiveness in handling complex spatial features in audio data, while theRNN provided valuable insights into sequential patterns. This Result highlights CNN’s advantages incapturing the intricacies of genre classification for culturally rich music forms like Carnatic. Futureresearch will focus on increasing the performance of such models, and leveraging both spatial andtemporal dimensions in audio might happen using hybrid CNN-RNN architectures. Also, this researchcontributes to the advancement of technology around music classification with promising avenues tocultural preservation and digital archiving of music.]]>
Copyrights © 2024
