Abstract | ||
---|---|---|
We introduce an audio texture synthesis algorithm based on scattering moments. A scattering transform is computed by iteratively decomposing a signal with complex wavelet filter banks and computing their amplitude envelop. Scattering moments provide general representations of stationary processes computed as expected values of scattering coefficients. They are estimated with low variance estimators from single realizations. Audio signals having prescribed scattering moments are synthesized with a gradient descent algorithms. Audio synthesis examples show that scattering representation provide good synthesis of audio textures with much fewer coefficients than the state of the art. |
Year | Venue | Field |
---|---|---|
2013 | CoRR | Audio signal,Artificial intelligence,Scattering,Amplitude,Texture synthesis,Computer vision,Gradient descent,Algorithm,Audio synthesis,Expected value,Statistics,Mathematics,Estimator |
DocType | Volume | Citations |
Journal | abs/1311.0407 | 11 |
PageRank | References | Authors |
0.81 | 1 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
J. Bruna | 1 | 1697 | 82.95 |
Stéphane Mallat | 2 | 110 | 9.92 |