# Deep scattering network for speech emotion recognition

arXiv: https://arxiv.org/abs/2105.04806 · HTML: https://mlsanity.com/paper/2105.04806/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 27 references that are in the map.
- First posted on arXiv 11 May 2021.

## Builds on (most cited first, 7 of 7)

- [The Mythos of Model Interpretability](https://mlsanity.com/paper/1606.03490/) (2016)
- [Deep Learning is Robust to Massive Label Noise](https://mlsanity.com/paper/1705.10694/) (2017)
- [Deep Scattering Spectrum](https://mlsanity.com/paper/1304.6763/) (2013)
- [Joint Time-Frequency Scattering](https://mlsanity.com/paper/1807.08869/) (2018)
- [Time-Frequency Scattering Accurately Models Auditory Similarities Between Instrumental Playing Techniques](https://mlsanity.com/paper/2007.10926/) (2020)
- [Audio Texture Synthesis with Scattering Moments](https://mlsanity.com/paper/1311.0407/) (2013)
- [Non-linear frequency warping using constant-Q transformation for speech emotion recognition](https://mlsanity.com/paper/2102.04029/) (2021)

## Built on by (most cited first, 2 of 2)

- [Wavelet Scattering Transform for Improving Generalization in Low-Resourced Spoken Language Identification](https://mlsanity.com/paper/2310.00602/) (2023)
- [SigWavNet: Learning Multiresolution Signal Wavelet Network for Speech Emotion Recognition](https://mlsanity.com/paper/2502.00310/) (2025)

## Abstract (arXiv)

This paper introduces scattering transform for speech emotion recognition (SER). Scattering transform generates feature representations which remain stable to deformations and shifting in time and frequency without much loss of information. In speech, the emotion cues are spread across time and localised in frequency. The time and frequency invariance characteristic of scattering coefficients provides a representation robust against emotion irrelevant variations e.g., different speakers, language, gender etc. while preserving the variations caused by emotion cues. Hence, such a representation captures the emotion information more efficiently from speech. We perform experiments to compare scattering coefficients with standard mel-frequency cepstral coefficients (MFCCs) over different databases. It is observed that frequency scattering performs better than time-domain scattering and MFCCs. We also investigate layer-wise scattering coefficients to analyse the importance of time shift and deformation stable scalogram and modulation spectrum coefficients for SER. We observe that layer-wise coefficients taken independently also perform better than MFCCs.