• Naman Kothari

This project was primarily aimed at creating an automated system for classifying music genre models. The first step was to find a good feature that clearly demarcates the boundaries of the genre. The most common characteristic that can be extracted from sound is the Mel Frequency Cepstral Coefficient (MFCC). MFCC representing the Mel Frequency cepstral coefficient. The input to CNN is a short-time Fourier transform of the audio signal. The output of the CNN is passed to another deep neural network for classification. There are many ways to classify songs by genre using song libraries, machine learning techniques, input formats, and neural networks. The spectrogram generated by the time song server is used as a record for a neural network (NN).

Classification of Music Genre, Convolutional Neural Networks, Feature Extraction, Mel Spectrogram, GITZAN dataset

"MUSIC GENRE CLASSIFICATION USING NEURAL NETWORK ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 4, page no.d420-d424, April-2022, Available :http://www.jetir.org/papers/JETIR2204355.pdf

"MUSIC GENRE CLASSIFICATION USING NEURAL NETWORK ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 4, page no. ppd420-d424, April-2022, Available at : http://www.jetir.org/papers/JETIR2204355.pdf