LASAFT: Latent source attentive frequency transformation for conditioned source separation

Woosung Choi, Minseok Kim, Jaehwa Chung, Soonyoung Jung

Research output: Contribution to journalConference articlepeer-review

Abstract

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.

Original languageEnglish
Pages (from-to)171-175
Number of pages5
JournalICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2021-June
DOIs
Publication statusPublished - 2021
Event2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
Duration: 2021 Jun 62021 Jun 11

Keywords

  • Attention
  • Conditioned source separation

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'LASAFT: Latent source attentive frequency transformation for conditioned source separation'. Together they form a unique fingerprint.

Cite this