Music similarity model based on CRP fusion and Multi-Kernel Integration

Abstract

Listen

Translate article

A music similarity model that combines Cross Recurrence Plot (CRP) fusion and Multi-Kernel Integration (MKI) is proposed for Cover Song Identification (CSI) task. First, two complementary descriptors: Harmonic Pitch Class Profile (HPCP), which represents the harmonic progression, and MeLoDy (MLD), which describes the melody evolution, are extracted from each track. Then, the CRP between each pair of tracks is constructed based on HPCP descriptor and MLD descriptor, respectively. To take advantage of the complementarity between the recurrence properties described by the HPCP based and MLD based CRPs, nonlinear graph fusion technique is adopted to fuse them to obtain the fused CRP. Next, recurrence quantification analysis is applied to the fused CRP to obtain the similarity score. Finally, MKI is introduced to refine the obtained similarity score to make it fit for diverse statistical characteristics of the tracks. Experimental results on three cover song datasets verify the superiority of the proposed model, in terms of identification accuracy and classification accuracy, over state-of-the-art CSI schemes based on single similarity function or similarity fusion. The proposed model can be modified and applied in other tasks, such as image classification, visual object tracking, and drug taxonomy, etc.