English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

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

ByteCover: Cover Song Identification via Multi-Loss Training