# Joint Time-Frequency Scattering for Audio Classification

arXiv: https://arxiv.org/abs/1512.02125 · HTML: https://mlsanity.com/paper/1512.02125/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Dec 2015.

## Built on by (most cited first, 8 of 8)

- [Parametric Scattering Networks](https://mlsanity.com/paper/2107.09539/) (2021)
- [Differentiable Time-Frequency Scattering on GPU](https://mlsanity.com/paper/2204.08269/) (2022)
- [Energy Propagation in Scattering Convolution Networks Can Be Arbitrarily Slow](https://mlsanity.com/paper/2406.05121/) (2024)
- [Cortical Features for Defense Against Adversarial Audio Attacks](https://mlsanity.com/paper/2102.00313/) (2021)
- [Interferometric Graph Transform for Community Labeling](https://mlsanity.com/paper/2106.05875/) (2021)
- [Time-Frequency Localization Using Deep Convolutional Maxout Neural Network in Persian Speech Recognition](https://mlsanity.com/paper/2108.03818/) (2021)
- [Evaluating Loss Functions in Differentiable Out-of-Domain Sound-Matching with Partial Parameter Distance](https://mlsanity.com/paper/2608.27698/) (2026)
- [WST-Graph: Topology-Preserving Wavelet Scattering Front-End for Speech Deepfake Detection](https://mlsanity.com/paper/2609.29372/) (2026)

## Abstract (arXiv)

We introduce the joint time-frequency scattering transform, a time shift invariant descriptor of time-frequency structure for audio classification. It is obtained by applying a two-dimensional wavelet transform in time and log-frequency to a time-frequency wavelet scalogram. We show that this descriptor successfully characterizes complex time-frequency phenomena such as time-varying filters and frequency modulated excitations. State-of-the-art results are achieved for signal reconstruction and phone segment classification on the TIMIT dataset.