Learning Separated Representations for Instrument-based Music Similarity

Abstract

A flexible recommendation and retrieval system requires music similarity in terms of multiple partial elements of musical pieces to allow users to select the element they want to focus on. A method for music similarity learning using multiple networks with individual instrumental signals is effective but faces the problem that using each clean instrumental signal as a query is impractical for retrieval systems and using separated instrumental signals reduces accuracy owing to artifacts. In this paper, we present instrumental-part-based music similarity learning with a single network that takes mixed signals as input instead of individual instrumental signals. Specifically, we designed a single similarity embedding space with separated subspaces for each instrument, extracted by Conditional Similarity Networks, which are trained using the triplet loss with masks. Experimental results showed that (1) the proposed method can obtain more accurate embedding representation than using individual networks using separated signals as input in the evaluation of an instrument that had low accuracy, (2) each sub-embedding space can hold the characteristics of the corresponding instrument, and (3) the selection of similar musical pieces focusing on each instrumental sound by the proposed method can obtain human acceptance, especially when focusing on timbre.