CWS-PResUNet: Music Source Separation with Channel-wise Subband Phase-aware ResUNet

Understand

Music source separation (MSS) shows active progress with deep learning models in recent years.

• Many MSS models perform separations on spectrograms by estimating bounded ratio masks and reusing the phases of the mixture.
• When using convolutional neural networks (CNN), weights are usually shared within a spectrogram during convolution regardless of the different patterns between frequency bands.
• In this study, we propose a new MSS model, channel-wise subband phase-aware ResUNet (CWS-PResUNet), to decompose signals into subbands and estimate an unbound complex ideal ratio mask (cIRM) for each source.