Demonstration: V2_large

Comparison with LaSAFT-Net-v1 (a.k.a. LaSAFT+GPoCM)

In this section, we provide audio samples extracted by using LASAFT-Net-v2. We use the same tracks used in the demonstartion of LaSAFT-Net-v1. LaSAFT-Net-v1 is our previous version, proposed in the paper “Latent Source Attentive Frequency Transformation for Conditioned Source Separation”.

Official Github Repo : ws-choi/Conditioned-Source-Separation-LaSAFT

Paper : arXiv

Track Infomation

  1. Vanishing paycheck - Stella Jang

  2. Villain - Stella Jang

  3. La Vie EN Rose - Stella Jang

  4. Feel this breeze - (Prod. JoeSwan) - HyungWoo & Sunmin

  5. Keep the Love Alive - Kyul, TM

  6. HongJinHo - GUIN

  7. 두근대 - Sllo

  8. Ms. Seductive - Jeff Bernat (cover) - Woosung Choi

  9. Footprints - Woosung Choi

  10. Rain - Woosung Choi

Preliminaries

!pip install git+https://github.com/ws-choi/LASAFT-Net-v2.git/ --quiet