Combining F0 and non-negative constraint robust principal component analysis for singing voice separation

摘要

Separating singing voice from a musical mixture remains an important task in the field of music information retrieval.Recent studies on singing voice separation have shown that robust principal component analysis (RPCA) with rank-1 constraint approach can improve separation quality.However.the performance of separation is limited because the vocal part can not be described well by the separated matrix.Therefore.prior information such as fundamental frequency (F0) should be considered.F0 can significantly improve separation performance by removing the spectral components of non-repeating instruments (e.g..bass and guitar).In this paper.we propose a novel singing voice separation algorithm by combining prior information and non-negative constraint RPCA.which incorporates F0 and non-negative rank-1 constraint minimization of singular values in RPCA instead of minimizing the nuclear norm.In addition.we use the original phase recovery in estimating the spectral components of the separated singing voice.Experimental results on the iKala and MIR-1K datasets show higher efficiency of the proposed algorithm compared with state-of-the-art methods in terms of separation accuracy.