Towards interpretable emotion recognition: Identifying key features with machine learning

TL;DR

This paper develops a machine learning framework to identify key interpretable features for emotion recognition, addressing the lack of interpretability in unsupervised audio models and enhancing their applicability in sensitive domains.

Contribution

It introduces a novel, robust approach to determine important interpretable features for emotion recognition, overcoming limitations of previous narrow-context studies.

Findings

Identified key interpretable features relevant to emotion recognition.

Provided a generalized framework applicable across different contexts.

Enhanced understanding of feature relevance in unsupervised audio models.

Abstract

Unsupervised methods, such as wav2vec2 and HuBERT, have achieved state-of-the-art performance in audio tasks, leading to a shift away from research on interpretable features. However, the lack of interpretability in these methods limits their applicability in critical domains like medicine, where understanding feature relevance is crucial. To better understand the features of unsupervised models, it remains critical to identify the interpretable features relevant to a given task. In this work, we focus on emotion recognition and use machine learning algorithms to identify and generalize the most important interpretable features for this task. While previous studies have explored feature relevance in emotion recognition, they are often constrained by narrow contexts and present inconsistent findings. Our approach aims to overcome these limitations, providing a broader and more robust framework for identifying the most important interpretable features.