Similarity fusion scheme for cover song identification

Abstract

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.

Two-layer similarity fusion model for cover song identification

“…It can be seen that: i) For HPCP-MLD (or BSC-CPCP) based combination, 2L-Best1 scheme performs much better than 1L-HPCP-QD [32] (or 1L-BSC-QD) or 1L-MLD-QD (or 1L-CPCP-QD) scheme in terms of all evaluation measures on all four datasets except for CA on DB802 (where the gap is smaller than 0.005%), which verifies the necessity and validity of the late fusion. ii) For HPCP-MLD based combination, 2L-Best1 scheme performs much better than state-of-the-art fusion based CSI schemes [24,26,31] and PSO based one in terms of identification accuracy and classification efficiency on all four datasets, except for the TNR on DB962, where PSO scheme achieves higher TNR at the sacrifice of much lower CA. iii) For BSC-CPCP based combination, 2L-Best1 scheme performs much better than the fusion based CSI scheme in [31] and PSO based one in terms of identification accuracy and classification efficiency on all four datasets.…”

“…In [31], the fusion of different similarities was achieved by projecting all similarities in a multi-dimensional space, where the dimensionality of this space was the number of similarities considered. In [26], the similarities based on different descriptors and corresponding similarity functions were obtained first. Then, the Similarity Network Fusion (SNF) technique [34] was used to fuse the similarity communities based on each similarity.…”

“…They are two-layer fusion with best learning method (2L-Best1), two-layer fusion when HPCP is considered (2L-HPCP-Best1), early fusion based on HPCP descriptor (1L-HPCP-QD) [32] and on MLD descriptor (1L-MLD-QD), the schemes proposed in [24,26], and [31], and the Particle Swarm Optimization (PSO) based one. In PSO based scheme, the similarities used in this work, HPCP+Qmax, HPCP+Dmax, MLD+Qmax and MLD+Dmax, are weighted and added together, and the optimal weight combination is sought by PSO technique [41].…”

“…In PSO based scheme, the similarities used in this work, HPCP+Qmax, HPCP+Dmax, MLD+Qmax and MLD+Dmax, are weighted and added together, and the optimal weight combination is sought by PSO technique [41]. For the fusion schemes in [26] and [24] 4 , the fused objects are those provided in [26] and [24], respectively. Unfortunately, we can not obtain the implementation of the pitch salience function used in [31], so the fused objects for [31] are those used in this work.…”

“…To solve this problem, some researchers began to study descriptor or similarity fusion models for the CSI task [22][23][24][25][26] (see Section 2). In this paper, we propose a two-layer similarity fusion model for the CSI task aiming at enhancing the identification accuracy and classification efficiency further.…”