Audio Texture Synthesis with Scattering Moments

2013/11/02 by Joan Bruna, Bruna, Joan, Stéphane Mallat +1 · 2 citations
Computer Science · #Applications (stat.AP) #FOS: Computer and information sciences #Music Technology and Sound Studies #Music and Audio Processing #Sound (cs.SD) #Speech and Audio Processing

paper · pdf · doi:10.48550/arxiv.1311.0407

openalex publication_date 2013/11/02 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Cited by

• Scaling the Scattering Transform: Deep Hybrid Networks
• wav2shape: Hearing the Shape of a Drum Machine

Related

• The Shape of RemiXXXes to Come: Audio Texture Synthesis with Time-frequency Scattering
• Sound texture synthesis using RI spectrograms
• Transformée en scattering sur la spirale temps-chroma-octave
• A Statistics-Driven Differentiable Approach for Sound Texture Synthesis and Analysis
• Synthesizing Diverse, High-Quality Audio Textures