Recent deep-learning approaches have shown that Frequency Transformation (FT) blocks can significantly improve spectrogram-based single-source separation models by capturing frequency patterns. The goal of this paper is to extend the FT block to fit the multi-source task. We propose the Latent Source Attentive Frequency Transformation (LaSAFT) block to capture source-dependent frequency patterns. We also propose the Gated Point-wise Convolutional Modulation (GPoCM), an extension of Feature-wise Linear Modulation (FiLM), to modulate internal features. By employing these two novel methods, we extend the Conditioned-U-Net (CUNet) for multi-source separation, and the experimental results indicate that our LaSAFT and GPoCM can improve the CUNet's performance, achieving state-of-the-art SDR performance on several MUSDB18 source separation tasks.
@article{arxiv.2010.11631,
title = {LaSAFT: Latent Source Attentive Frequency Transformation for Conditioned Source Separation},
author = {Woosung Choi and Minseok Kim and Jaehwa Chung and Soonyoung Jung},
journal= {arXiv preprint arXiv:2010.11631},
year = {2021}
}
Comments
5 pages, 3 figures, 2 tables. accepted to ICASSP 2021