Audio Texture Synthesis with Scattering Moments

By Joan Bruna, Stéphane Mallat. 2013

49 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition, Speech & Audio, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Speech & Audio

In Signal Processing

Citations in the corpus

Scattering Networks for Hybrid Representation Learning (2018, methodology): “This representation has been proved to linearize small deformations of images [35], be non-expansive and almost complete [10], [17], which makes it an ideal input to a deep network algorithm, which can build invariants to this local variability via a first linear operator.”
Scaling the Scattering Transform: Deep Hybrid Networks (2017, positive): “This representation is proved to linearize small deformations [24] of images, be non-expansive and almost complete [10, 5], which makes it an ideal input to a deep network algorithm, that can build invariants to this local variability via a first linear operator.”
Wavelet Scattering Regression of Quantum Chemical Energies (2016, background): “They have found applications for image [43, 11] and audio [10, 2] signal classifications.”
Super-Resolution with Deep Convolutional Sufficient Statistics (2015, background): “Whereas scattering networks used in recognition applications typically contain only steerable ﬁlters (Bruna & Mallat (2013)), in our setup it is worth pointing out that one can recover traditional total variation norms by properly adjusting the ﬁrst wavelet decomposition.”