Bottom-up Broadcast Neural Network For Music Genre Classification
This work addresses the challenge of adapting CNNs for music genre recognition, which is important for applications in music organization and recommendation, though it appears incremental as it builds on existing CNN methods.
The paper tackled the problem of music genre classification by developing a novel CNN architecture that exploits low-level spectrogram information and long contextual information, achieving excellent performances on benchmark datasets like GTZAN, Ballroom, and Extended Ballroom.
Music genre recognition based on visual representation has been successfully explored over the last years. Recently, there has been increasing interest in attempting convolutional neural networks (CNNs) to achieve the task. However, most of existing methods employ the mature CNN structures proposed in image recognition without any modification, which results in the learning features that are not adequate for music genre classification. Faced with the challenge of this issue, we fully exploit the low-level information from spectrograms of audios and develop a novel CNN architecture in this paper. The proposed CNN architecture takes the long contextual information into considerations, which transfers more suitable information for the decision-making layer. Various experiments on several benchmark datasets, including GTZAN, Ballroom, and Extended Ballroom, have verified the excellent performances of the proposed neural network. Codes and model will be available at "ttps://github.com/CaifengLiu/music-genre-classification".