README.md

November 15, 2021 ยท View on GitHub

LASAFT-Net-v2

Listen, Attend and Separate by Attentively aggregating Frequency Transformation

Woosung Choi, Yeong-Seok Jeong, Jinsung Kim, Jaehwa Chung, Soonyoung Jung, and Joshua D. Reiss

Demonstration (under construction)

Experimental Results

  • Musdb 18
modelvocalsdrumsbassotherAVG
Meta-TasNet6.405.915.584.195.52
AMSS-Net6.785.925.104.515.58
LaSAFT-Net-v17.335.685.634.875.88
LASAFT-Net-v27.576.135.284.875.96
modelmodel typevocalsdrumsbassotherAVG
KUILAB-MDX-Netdedicated (1 source/ 1 model)8.9017.1737.2325.6367.236
LaSAFT-Net-v1 (light)conditioned (4 sources/ 1 model)7.2755.9355.8234.5575.897
LASAFT-Net-v2 (light)conditioned (4 sources/ 1 model)7.3245.9765.8844.6425.957

How to reproduce

1. Environment

  • Ubuntu 20.04
  • wandb for logging

You must create .env file by copying .env.sample to set environmental variables.

wandb_api_key=[Your Key] # "xxxxxxxxxxxxxxxxxxxxxxxx"
data_dir=[Your Path] # "/home/ielab/repos/musdbHQ"
  • about wandb_api_key
    • we currently only support wandb for logging.
    • for wandb_api_key, visit wandb, go to setting, and then copy your api key
  • about data_dir
    • the absolute path where datasets are stored

2. Installation (cuda)

conda env create -f environment.yaml -n lasaftv2
conda activate lasaftv2
pip install -r requirements.txt