A Hybrid CNN-LSTM Architecture for Enhanced Music Genre Classification

This paper presents a study on the effectiveness of integrating Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks for music genre classification. By combining CNN's ability to extract spatial features from audio data with LSTM's capacity to capture temporal dependencies, the hybrid CNN-LSTM model shows superior performance over traditional models. The experiments conducted on ten different music genres demonstrate that the proposed approach achieves higher classification accuracy, particularly in genres with complex temporal structures like Rock, Pop, and Hip-Hop. The results highlight the potential of this architecture in improving genre classification tasks.