# Disentanglement for audio-visual emotion recognition using multitask setup

arXiv: https://arxiv.org/abs/2102.06269 · HTML: https://mlsanity.com/paper/2102.06269/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Feb 2021.

## Built on by (most cited first, 3 of 3)

- [Leveraging Label Information for Multimodal Emotion Recognition](https://mlsanity.com/paper/2309.02106/) (2023)
- [Towards Disentangled Speech Representations](https://mlsanity.com/paper/2208.13191/) (2022)
- [Dynamic Causal Disentanglement Model for Dialogue Emotion Detection](https://mlsanity.com/paper/2309.06928/) (2023)

## Abstract (arXiv)

Deep learning models trained on audio-visual data have been successfully used to achieve state-of-the-art performance for emotion recognition. In particular, models trained with multitask learning have shown additional performance improvements. However, such multitask models entangle information between the tasks, encoding the mutual dependencies present in label distributions in the real world data used for training. This work explores the disentanglement of multimodal signal representations for the primary task of emotion recognition and a secondary person identification task. In particular, we developed a multitask framework to extract low-dimensional embeddings that aim to capture emotion specific information, while containing minimal information related to person identity. We evaluate three different techniques for disentanglement and report results of up to 13% disentanglement while maintaining emotion recognition performance.