Published August 10, 2021 | Version v1
Other Open

2021 ISMIR MSS Challenge - ByteMSS team - pretrained model

Authors/Creators

  • 1. ByteDance

Description

The model I submitted in the 2021 ISMIR MSS Challenge with 2nd performance on the vocal score and 5th performance on the overall score on Leaderboard A.

AIcrowd | Music Demixing Challenge @ISMIR 2021 | Leaderboards

Files

Files (1.3 GB)

Name Size
md5:3d0cce24aaca74b9bf7d706f2ef96be6
425.9 MB Download
md5:8d153a287f16d11172b1a17b4e700fd0
904.0 MB Download

Additional details

References

  • Liu, H., Xie, L., Wu, J., & Yang, G. (2020). Channel-wise subband input for better voice and accompaniment separation on high resolution music. arXiv preprint arXiv:2008.05216.