• MAHEK SHARMA
• Siddid Kaul
• Ishika Singh

—Machine learning (ML) and artificial intelligence (AI) have emerged as transformative technologies across numerous sectors, including music analysis. Music genre classification, a complex task within music information retrieval, involves extracting significant audio features to accurately categorize music. This research investigates various ML algorithms for music genre classification, evaluating their performance on the GTZAN dataset. The study encompasses traditional classifiers, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and hybrid models. Results indicate accuracies from 40% to 95%, with CNN-RNN hybrid models, specifically convolution-recurrent neural networks (CRNNs), demonstrating superior performance. Additionally, ensemble methods like AdaBoost were found to enhance classification accuracy. This work contributes to the field by exploring effective music genre classification strategies, particularly emphasizing parallel and ensemble techniques.

Convolution-Recurrent Neural Networks, Ensemble Learning, Music Genre Classification, Music Information Retrieval

"MUSIC GENRE CLASSIFIER USING MACHINE LEARNING ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.g174-g178, April-2024, Available :http://www.jetir.org/papers/JETIR2404618.pdf

"MUSIC GENRE CLASSIFIER USING MACHINE LEARNING ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppg174-g178, April-2024, Available at : http://www.jetir.org/papers/JETIR2404618.pdf