Music Genre Classification Using LSTM and CNN

In this comparative study of various machine learning techniques for music genre classification. Music genre classification is a challenging task due to the subjective nature of music and the lack of clear boundaries between genres. This study intends to design and develop a novel deep learning model based on a combination of different deep learning algorithms such as LSTM and CNN and train them on a dataset of audio features extracted from a large collection of music tracks. We also explored the impact of various traditional features and devised a new variety rich feature-set and analyzed their impact on the classification accuracy. Here, the performance is measured by using GTZAN dataset