Applying visual domain style transfer and texture synthesis techniques to audio: insights and challenges

@article{Huzaifah2019ApplyingVD,
  title={Applying visual domain style transfer and texture synthesis techniques to audio: insights and challenges},
  author={Muhammad Huzaifah and Lonce L. Wyse},
  journal={Neural Computing and Applications},
  year={2019},
  pages={1-15}
}
Style transfer is a technique for combining two images based on the activations and feature statistics in a deep learning neural network architecture. This paper studies the analogous task in the audio domain and takes a critical look at the problems that arise when adapting the original vision-based framework to handle spectrogram representations. We conclude that CNN architectures with features based on 2D representations and convolutions are better suited for visual images than for time… CONTINUE READING
1
Twitter Mention

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 41 REFERENCES

Audio texture synthesis and style transfer. URL https://dmitryulyanov.github.io/ audio-texture-synthesis-and-style-transfer

D Ulyanov, V Lebedev
  • 2016
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

Sound texture modelling with linear prediction in both time and frequency domains

  • 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).
  • 2003
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

A (2017) Multi-style transfer: Generalizing fast style transfer to several genres

B Cui, C Qi, Wang
  • 2017
VIEW 1 EXCERPT

A (2017) Style transfer for prosodic speech

A Perez, C Proctor, Jain
  • 2017
VIEW 2 EXCERPTS

Audio Style Transfer

  • 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2017
VIEW 2 EXCERPTS