Music Auto-Tagging with Capsule Network

• 作者: Feng Mai Minhui Qi Quanxin Deng Yifan Tang Yongbin Yu Zhaxi Nima
• 来源期刊: 国际计算机前沿大会会议论文集
• 学科: 工学
• 关键词: Convolutional neural networks Music Information Retrieval Music auto-tagging Capsule network
• 年，卷（期）: 2020,（1）
• 页码范围: 292-298
• 页数: 7页
• 分类号: TN9

摘要

In recent years,convolutional neural networks(CNNs)become popular approaches used in music information retrieval(MIR)tasks,such as mood recognition,music auto-tagging and so on.Since CNNs are able to extract the local features effectively,previous attempts show great performance on music auto-tagging.However,CNNs is not able to capture the spatial features and the relationship between low-level features are neglected.Motivated by this problem,a hybrid architecture is proposed based on Capsule Network,which is capable to extract spatial features with the routing-by-agreement mechanism.The proposed model was applied in music auto-tagging.The results show that it achieves promising results of the ROC-AUC score of 90.67%.