文献类型：期刊文献

英文题名：Similarity fusion scheme for cover song identification

作者：Chen, Ning[1];Xiao, Hai-dong[2]

机构：[1]E China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]Chinese Acad Sci, Shanghai Adv Res Inst, Shanghai 201210, Peoples R China

年份：2016

卷号：52

期号：13

起止页码：1173

外文期刊名：ELECTRONICS LETTERS

收录：;EI(收录号：20162502528442);WOS:【SCI-EXPANDED(收录号:WOS:000378886300046)】；

基金：This work was supported by the National Natural Science Foundation of China (61271349).

语种：英文

摘要：To take advantage of the complementarity of different features in representing the common facets shared among cover versions, the similarity network fusion strategy in biological field is adopted to fuse the cochlear pitch class profile (PCP), beat-synchronous chroma and harmonic PCP feature-based similarity networks for cover song identification. For a music collection, first, the similarity network based on each feature and corresponding similarity measure is generated; then, the similarity network fusion method is used to fuse these similarity networks to create the fused similarity network; finally, the similarity scores in fused similarity network are used to train a classifier, which can then be used to identify whether the corresponding tracks are reference/cover or reference/non-cover pair according to the input similarity value. Experimental results demonstrated that the proposed scheme not only realised general classification with high accuracy, but also outperformed the state-of-the-art schemes in high-score evaluation and defining cover versions community.