# Audio Texture Synthesis with Scattering Moments

arXiv: https://arxiv.org/abs/1311.0407 · HTML: https://mlsanity.com/paper/1311.0407/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2013.

## Built on by (most cited first, 4 of 4)

- [Generalized Recorrupted-to-Recorrupted: Self-Supervised Learning Beyond Gaussian Noise](https://mlsanity.com/paper/2412.04648/) (2024)
- [Deep scattering network for speech emotion recognition](https://mlsanity.com/paper/2105.04806/) (2021)
- [Wavelet Scattering Transform for Improving Generalization in Low-Resourced Spoken Language Identification](https://mlsanity.com/paper/2310.00602/) (2023)
- [TimberAgent: Gram-Guided Retrieval for Executable Music Effect Control](https://mlsanity.com/paper/2603.09332/) (2026)

## Abstract (arXiv)

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.