Nikita Prudnikov

Support for multi-channel audio

4

Hi! I've added an option to train the network on a stereo material. Hypothesis is that extra channels on just first and last conv layers are enough because l/r channels...

https://github.com/kewellcjj/pytorch-multiple-style-transfer/blob/a295854382b45076c3f3c334dd6f88e50014fe1a/transformer_net.py#L82 In the original TF implementation the instancenorm layers in the residual blocks are also conditioned as far as I understand. Leaving them unconditioned in current implementation may lead to...

https://ccrma.stanford.edu/~jos/swgt/Digital_Waveguide.html multidimensional strings

https://link.springer.com/chapter/10.1007/978-1-4615-0049-0_5 http://gamma.cs.unc.edu/AUDIO_MATERIAL/examplebasedsoundsynthesis.pdf http://persianney.com/kvdoelcsubc/publications/modalpaper.pdf https://forum.mutable-instruments.net/t/modal-synthesis/13254/6 https://en.wikipedia.org/wiki/Volterra_series

reference PR here, not to merge