# Does Visual Self-Supervision Improve Learning of Speech Representations for Emotion Recognition?

arXiv: https://arxiv.org/abs/2005.01400 · HTML: https://mlsanity.com/paper/2005.01400/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 May 2020.

## Built on by (most cited first, 9 of 9)

- [Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection](https://mlsanity.com/paper/2201.07131/) (2022)
- [Audio Self-supervised Learning: A Survey](https://mlsanity.com/paper/2203.01205/) (2022)
- [Jointly Learning Visual and Auditory Speech Representations from Raw Data](https://mlsanity.com/paper/2212.06246/) (2022)
- [LiRA: Learning Visual Speech Representations from Audio through Self-supervision](https://mlsanity.com/paper/2106.09171/) (2021)
- [Self-supervised EEG Representation Learning for Automatic Sleep Staging](https://mlsanity.com/paper/2110.15278/) (2021)
- [Self-supervised Graphs for Audio Representation Learning with Limited Labeled Data](https://mlsanity.com/paper/2202.00097/) (2022)
- [Self-Supervised Learning for Audio-Based Emotion Recognition](https://mlsanity.com/paper/2307.12343/) (2023)
- [Leveraging Unlabeled Audio-Visual Data in Speech Emotion Recognition using Knowledge Distillation](https://mlsanity.com/paper/2507.00055/) (2025)
- [Unrequited Emotions: Investigating the Gaps in Motivation and Practice in Speech Emotion Recognition Research](https://mlsanity.com/paper/2604.25776/) (2026)

## Abstract (arXiv)

Self-supervised learning has attracted plenty of recent research interest. However, most works for self-supervision in speech are typically unimodal and there has been limited work that studies the interaction between audio and visual modalities for cross-modal self-supervision. This work (1) investigates visual self-supervision via face reconstruction to guide the learning of audio representations; (2) proposes an audio-only self-supervision approach for speech representation learning; (3) shows that a multi-task combination of the proposed visual and audio self-supervision is beneficial for learning richer features that are more robust in noisy conditions; (4) shows that self-supervised pretraining can outperform fully supervised training and is especially useful to prevent overfitting on smaller sized datasets. We evaluate our learned audio representations for discrete emotion recognition, continuous affect recognition and automatic speech recognition. We outperform existing self-supervised methods for all tested downstream tasks. Our results demonstrate the potential of visual self-supervision for audio feature learning and suggest that joint visual and audio self-supervision leads to more informative audio representations for speech and emotion recognition.