ByteCover: Cover Song Identification via Multi-Loss Training

27 Oct 2020  ·  Xingjian Du, Zhesong Yu, Bilei Zhu, Xiaoou Chen, Zejun Ma ·

We present in this paper ByteCover, which is a new feature learning method for cover song identification (CSI). ByteCover is built based on the classical ResNet model, and two major improvements are designed to further enhance the capability of the model for CSI. In the first improvement, we introduce the integration of instance normalization (IN) and batch normalization (BN) to build IBN blocks, which are major components of our ResNet-IBN model. With the help of the IBN blocks, our CSI model can learn features that are invariant to the changes of musical attributes such as key, tempo, timbre and genre, while preserving the version information. In the second improvement, we employ the BNNeck method to allow a multi-loss training and encourage our method to jointly optimize a classification loss and a triplet loss, and by this means, the inter-class discrimination and intra-class compactness of cover songs, can be ensured at the same time. A set of experiments demonstrated the effectiveness and efficiency of ByteCover on multiple datasets, and in the Da-TACOS dataset, ByteCover outperformed the best competitive system by 20.9\%.

PDF Abstract

Datasets


  Add Datasets introduced or used in this paper
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Cover song identification Covers80 ByteCover MAP 0.906 # 3
Cover song identification Da-TACOS ByteCover mAP 0.743 # 2
Cover song identification SHS100K-TEST ByteCover mAP 0.836 # 2
Cover song identification YouTube350 ByteCover MAP 0.955 # 2

Methods