Phase Shuffle is a technique for removing pitched noise artifacts that come from using transposed convolutions in audio generation models. Phase shuffle is an operation with hyperparameter $n$. It randomly perturbs the phase of each layer’s activations by −$n$ to $n$ samples before input to the next layer.
In the original application in WaveGAN, the authors only apply phase shuffle to the discriminator, as the latent vector already provides the generator a mechanism to manipulate the phase of a resultant waveform. Intuitively speaking, phase shuffle makes the discriminator’s job more challenging by requiring invariance to the phase of the input waveform.
Source: Adversarial Audio SynthesisPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Speech Synthesis | 4 | 17.39% |
Image Generation | 3 | 13.04% |
Voice Conversion | 3 | 13.04% |
Audio Generation | 2 | 8.70% |
Singing Voice Synthesis | 2 | 8.70% |
Image-to-Image Translation | 1 | 4.35% |
Translation | 1 | 4.35% |
Time Series Analysis | 1 | 4.35% |
Adversarial Robustness | 1 | 4.35% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |