Enrolment-based personalisation for improving individual-level fairness in speech emotion recognition

TL;DR

This paper introduces an enrolment-based personalization method for speech emotion recognition that adapts models to individual speakers using minimal data, aiming to improve fairness and performance across diverse users.

Contribution

It proposes a novel speaker-specific adaptation approach and evaluation schemes to better assess and enhance individual-level fairness in speech emotion recognition systems.

Findings

Personalization improves individual speaker performance.

New evaluation schemes reveal fairness issues hidden in aggregated metrics.

Method enhances both overall and speaker-specific accuracy.

Abstract

The expression of emotion is highly individualistic. However, contemporary speech emotion recognition (SER) systems typically rely on population-level models that adopt a `one-size-fits-all' approach for predicting emotion. Moreover, standard evaluation practices measure performance also on the population level, thus failing to characterise how models work across different speakers. In the present contribution, we present a new method for capitalising on individual differences to adapt an SER model to each new speaker using a minimal set of enrolment utterances. In addition, we present novel evaluation schemes for measuring fairness across different speakers. Our findings show that aggregated evaluation metrics may obfuscate fairness issues on the individual-level, which are uncovered by our evaluation, and that our proposed method can improve performance both in aggregated and disaggregated terms.