Published November 22, 2017 | Version v1
Software Open

Trained Models for "Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask"

Creators

  • 1. Fraunhofer-IDMT
  • 2. Audio Research Group, Dept. of Signal Processing, Tampere University of Technology, Tampere, Finland.
  • 3. University of Montreal, INRS-EMT
  • 4. University of Montreal

Description

Support material (binary files) for the following work: S.I. Mimilakis, K. Drossos, J.F. Santos, G. Schuller, T. Virtanen, Y. Bengio , "Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask", in arXiv:1711.01437 [cs.SD], Nov. 2017.

 

To be used here: https://github.com/Js-Mim/mss_pytorch

Files

torch_rinf_svs.pytorch.zip

Files (100.8 MB)

Name Size Download all
md5:57bdcca2e69d6f65795a83ce778f97df
100.8 MB Preview Download

Additional details

Related works

Is documented by
arXiv:1711.01437 (arXiv)

Funding

MacSeNet – Machine Sensing Training Network 642685
European Commission

References

  • S.I. Mimilakis, K. Drossos, J.F. Santos, G. Schuller, T. Virtanen, Y. Bengio , "Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask", in arXiv:1711.01437 [cs.SD], Nov. 2017.
  • S.I. Mimilakis, K. Drossos, J.F. Santos, G. Schuller, T. Virtanen, Y. Bengio , "Monaural Singing Voice Separation with Skip-Filtering Connections and Recurrent Inference of Time-Frequency Mask", in Proceedings of 43rd International Conference on Acoustics, Speech and Signal Processing (ICASSP 2018), April, 2018.