# Differentiable Time-Frequency Scattering on GPU

arXiv: https://arxiv.org/abs/2204.08269 · HTML: https://mlsanity.com/paper/2204.08269/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 24 references that are in the map.
- First posted on arXiv 18 Apr 2022.

## Builds on (most cited first, 11 of 11)

- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Kymatio: Scattering Transforms in Python](https://mlsanity.com/paper/1812.11214/) (2018)
- [Scattering Networks for Hybrid Representation Learning](https://mlsanity.com/paper/1809.06367/) (2018)
- [Parametric Scattering Networks](https://mlsanity.com/paper/2107.09539/) (2021)
- [Deep convolutional networks on the pitch spiral for musical instrument recognition](https://mlsanity.com/paper/1605.06644/) (2016)
- [Joint Time-Frequency Scattering](https://mlsanity.com/paper/1807.08869/) (2018)
- [Joint Time-Frequency Scattering for Audio Classification](https://mlsanity.com/paper/1512.02125/) (2015)
- [Extended playing techniques: The next milestone in musical instrument recognition](https://mlsanity.com/paper/1808.09730/) (2018)
- [Time-Frequency Scattering Accurately Models Auditory Similarities Between Instrumental Playing Techniques](https://mlsanity.com/paper/2007.10926/) (2020)
- [The Shape of RemiXXXes to Come: Audio Texture Synthesis with Time-frequency Scattering](https://mlsanity.com/paper/1906.09334/) (2019)
- [Joint Scattering for Automatic Chick Call Recognition](https://mlsanity.com/paper/2110.03965/) (2021)

## Built on by (most cited first, 1 of 1)

- [SCRAPL: Scattering Transform with Random Paths for Machine Learning](https://mlsanity.com/paper/2602.11145/) (2026)

## Abstract (arXiv)

Joint time-frequency scattering (JTFS) is a convolutional operator in the time-frequency domain which extracts spectrotemporal modulations at various rates and scales. It offers an idealized model of spectrotemporal receptive fields (STRF) in the primary auditory cortex, and thus may serve as a biological plausible surrogate for human perceptual judgments at the scale of isolated audio events. Yet, prior implementations of JTFS and STRF have remained outside of the standard toolkit of perceptual similarity measures and evaluation methods for audio generation. We trace this issue down to three limitations: differentiability, speed, and flexibility. In this paper, we present an implementation of time-frequency scattering in Python. Unlike prior implementations, ours accommodates NumPy, PyTorch, and TensorFlow as backends and is thus portable on both CPU and GPU. We demonstrate the usefulness of JTFS via three applications: unsupervised manifold learning of spectrotemporal modulations, supervised classification of musical instruments, and texture resynthesis of bioacoustic sounds.