Towards Interpretability in Audio and Visual Affective Machine Learning: A Review

TL;DR

This review examines recent progress in applying interpretability techniques to audio and visual affective machine learning, highlighting current limitations and proposing future research directions for transparent and fair affective AI systems.

Contribution

It provides a structured overview of the use of interpretability in affective machine learning with audio and visual data, identifying gaps and offering recommendations for future research.

Findings

Interpretability methods have emerged mainly in the last five years.

Current use of interpretability is limited in scope and depth.

There are significant gaps in evaluating and applying interpretability in affective ML.

Abstract

Machine learning is frequently used in affective computing, but presents challenges due the opacity of state-of-the-art machine learning methods. Because of the impact affective machine learning systems may have on an individual's life, it is important that models be made transparent to detect and mitigate biased decision making. In this regard, affective machine learning could benefit from the recent advancements in explainable artificial intelligence (XAI) research. We perform a structured literature review to examine the use of interpretability in the context of affective machine learning. We focus on studies using audio, visual, or audiovisual data for model training and identified 29 research articles. Our findings show an emergence of the use of interpretability methods in the last five years. However, their use is currently limited regarding the range of methods used, the depth of evaluations, and the consideration of use-cases. We outline the main gaps in the research and provide recommendations for researchers that aim to implement interpretable methods for affective machine learning.