Advanced search
1 file | 291.52 KB Add to list

A CycleGAN for style transfer between drum and bass subgenres

Len Vande Veire (UGent) , Tijl De Bie (UGent) and Joni Dambre (UGent)
Author
Organization
Abstract
In this work, we apply the CycleGAN image-to- image translation framework to Mel-scaled log- amplitude spectrograms, successfully realizing audio texture transfer between excerpts from two musically related genres. Such automatic musical transfer could provide music producers and DJs with new creative tools, e.g. to quickly prototype a remix of an existing song in another genre, or to use as an advanced effect during a live perfor- mance. We show that meaningful style transfer can be realized using only a limited amount of data and computational resources. A high-quality audio reconstruction is obtained from the gener- ated amplitude spectrogram by simply using the phase of the original audio as an approximation for the phase of the generated spectrogram. This results in a significant quality improvement over traditional phase reconstruction methods.

Downloads

  • DS228.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 291.52 KB

Citation

Please use this url to cite or link to this publication:

MLA
Vande Veire, Len, et al. “A CycleGAN for Style Transfer between Drum and Bass Subgenres.” ML4MD at ICML2019, Proceedings, 2019.
APA
Vande Veire, L., De Bie, T., & Dambre, J. (2019). A CycleGAN for style transfer between drum and bass subgenres. In ML4MD at ICML2019, Proceedings. Long Beach, USA.
Chicago author-date
Vande Veire, Len, Tijl De Bie, and Joni Dambre. 2019. “A CycleGAN for Style Transfer between Drum and Bass Subgenres.” In ML4MD at ICML2019, Proceedings.
Chicago author-date (all authors)
Vande Veire, Len, Tijl De Bie, and Joni Dambre. 2019. “A CycleGAN for Style Transfer between Drum and Bass Subgenres.” In ML4MD at ICML2019, Proceedings.
Vancouver
1.
Vande Veire L, De Bie T, Dambre J. A CycleGAN for style transfer between drum and bass subgenres. In: ML4MD at ICML2019, Proceedings. 2019.
IEEE
[1]
L. Vande Veire, T. De Bie, and J. Dambre, “A CycleGAN for style transfer between drum and bass subgenres,” in ML4MD at ICML2019, Proceedings, Long Beach, USA, 2019.
@inproceedings{8619952,
  abstract     = {In this work, we apply the CycleGAN image-to-
image translation framework to Mel-scaled log-
amplitude spectrograms,  successfully realizing
audio texture transfer between excerpts from two
musically related genres. Such automatic musical
transfer could provide music producers and DJs
with new creative tools, e.g. to quickly prototype
a remix of an existing song in another genre, or
to use as an advanced effect during a live perfor-
mance.  We show that meaningful style transfer
can be realized using only a limited amount of
data and computational resources. A high-quality
audio reconstruction is obtained from the gener-
ated amplitude spectrogram by simply using the
phase of the original audio as an approximation
for the phase of the generated spectrogram. This
results in a significant quality improvement over
traditional phase reconstruction methods.},
  author       = {Vande Veire, Len and De Bie, Tijl and Dambre, Joni},
  booktitle    = {ML4MD at ICML2019, Proceedings},
  language     = {eng},
  location     = {Long Beach, USA},
  pages        = {3},
  title        = {A CycleGAN for style transfer between drum and bass subgenres},
  url          = {https://sites.google.com/view/ml4md2019/home},
  year         = {2019},
}