DECOUPLING MAGNITUDE AND PHASE ESTIMATION WITH DEEP ResUNet FOR MUSIC SOURCE SEPARATION

Qiuqiang Kong, Yin Cao, Haohe Liu, Keunwoo Choi, Yuxuan Wang

Research output: Chapter in Book or Report/Conference proceedingChapterpeer-review

Abstract

Deep neural network based methods have been success-fully applied to music source separation. They typically learn a mapping from a mixture spectrogram to a set of source spectrograms, all with magnitudes only. This approach has several limitations: 1) its incorrect phase recon-struction degrades the performance, 2) it limits the magnitude of masks between 0 and 1 while we observe that 22% of time-frequency bins have ideal ratio mask values of over 1 in a popular dataset, MUSDB18, 3) its poten-tial on very deep architectures is under-explored. Our proposed system is designed to overcome these. First, we propose to estimate phases by estimating complex ideal ratio masks (cIRMs) where we decouple the estimation of cIRMs into magnitude and phase estimations. Sec-ond, we extend the separation method to effectively al-low the magnitude of the mask to be larger than 1. Fi-nally, we propose a residual UNet architecture with up to 143 layers. Our proposed system achieves a state-of-the-art MSS result on the MUSDB18 dataset, espe-cially, a SDR of 8.98 dB on vocals, outperforming the previous best performance of 7.24 dB. The source code is available at: https://github.com/bytedance/ music_source:separation.

Original languageEnglish
Title of host publicationProceedings of the International Society for Music Information Retrieval Conference
PublisherInternational Society for Music Information Retrieval
Pages342-349
Number of pages8
Publication statusPublished - 2021
Externally publishedYes

Publication series

NameProceedings of the International Society for Music Information Retrieval Conference
Volume2021
ISSN (Electronic)3006-3094

Fingerprint

Dive into the research topics of 'DECOUPLING MAGNITUDE AND PHASE ESTIMATION WITH DEEP ResUNet FOR MUSIC SOURCE SEPARATION'. Together they form a unique fingerprint.

Cite this