Hybrid architecture of a neural network for the problem of music classification
Бесплатный доступ
The issue of classifying musical genres with the help of various types of hybrid neural network based on a combination of convolutional and recurrent neural networks is considered. The paper aims to analyze the two models’ capability for music classification and determine which model is better suited for the task. These results shed light on guiding further exploration of computer music.
Neural network, convolutional neural network, recurrent neural network, music classification, gtzan mel-spectrogram
Короткий адрес: https://sciup.org/140300752
IDR: 140300752
Статья научная