Open AccessMusic Genre Classification using Spectral Analysis Techniques With Hybrid Convolution-Recurrent Neural Network
Author(s) -
Faiyaz Ahmad*,
Sahil Sahil
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.a3956.119119
Subject(s) - spectrogram , computer science , feature extraction , mel frequency cepstrum , short time fourier transform , convolutional neural network , artificial intelligence , pattern recognition (psychology) , speech recognition , convolution (computer science) , recurrent neural network , feature (linguistics) , artificial neural network , cepstrum , fourier transform , fourier analysis , mathematics , mathematical analysis , linguistics , philosophy
In this work, the objective is to classify the audio data into specific genres from GTZAN dataset which contain about 10 genres. First, it perform the audio splitting to make it signal into clips which contains homogeneous content. Short-term Fourier Transform (STFT), Mel-spectrogram and Mel-frequency cepstrum coefficient (MFCC) are the most common feature extraction technique and each feature extraction technique has been successful in their own various audio applications. Then, these feature extractions of the audio fed to the Convolution Neural Network (CNN) model and VGG16 Neural Network model, which consist of 16 convolution layers network. We perform different feature extraction with different CNN and VGG16 model with or without different Recurrent Neural Network (RNN) and evaluated performance measure. In this model, it has achieved overall accuracy 95.5\% for this task.