Generative Audio Models
WaveGlow
Introduced by Prenger et al. in WaveGlow: A Flow-based Generative Network for Speech SynthesisWaveGlow is a flow-based generative model that generates audio by sampling from a distribution. Specifically samples are taken from a zero mean spherical Gaussian with the same number of dimensions as our desired output, and those samples are put through a series of layers that transforms the simple distribution to one which has the desired distribution.
Source: WaveGlow: A Flow-based Generative Network for Speech Synthesis
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Speech Synthesis | 8 | 36.36% |
| Density Estimation | 2 | 9.09% |
| Speech Enhancement | 2 | 9.09% |
| Text-To-Speech Synthesis | 1 | 4.55% |
| Transliteration | 1 | 4.55% |
| Style Transfer | 1 | 4.55% |
| Audio Classification | 1 | 4.55% |
| Face Swapping | 1 | 4.55% |
| Synthetic Speech Detection | 1 | 4.55% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Affine Coupling
|
Bijective Transformation | |
Invertible 1x1 Convolution
|
Convolutions | |
Normalizing Flows
|
Distribution Approximation |
