Dynamic Time-Alignment of Dimensional Annotations of Emotion using Recurrent Neural Networks

TL;DR

This paper introduces a Recurrent Neural Network-based method to dynamically align and synchronize subjective, inconsistent emotion annotations from multiple annotators with acoustic features, improving agreement and prediction accuracy across diverse datasets.

Contribution

The proposed method effectively compensates annotation inconsistencies and enhances synchronization between annotations and audio features using RNNs, a novel approach in emotion recognition.

Findings

Significantly increased inter-annotator agreement.

Improved correlation between annotations and acoustic features.

Enhanced emotion prediction accuracy, especially for valence and arousal.

Abstract

Most automatic emotion recognition systems exploit time-continuous annotations of emotion to provide fine-grained descriptions of spontaneous expressions as observed in real-life interactions. As emotion is rather subjective, its annotation is usually performed by several annotators who provide a trace for a given dimension, i.e. a time-continuous series describing a dimension such as arousal or valence. However, annotations of the same expression are rarely consistent between annotators, either in time or in value, which adds bias and delay in the trace that is used to learn predictive models of emotion. We therefore propose a method that can dynamically compensate inconsistencies across annotations and synchronise the traces with the corresponding acoustic features using Recurrent Neural Networks. Experimental evaluations were carried on several emotion data sets that include Chinese, French, German, and Hungarian participants who interacted remotely in either noise-free conditions or in-the-wild. The results show that our method can significantly increase inter-annotator agreement, as well as correlation between traces and audio features, for both arousal and valence. In addition, improvements are obtained in the automatic prediction of these dimensions using simple light-weight models, especially for valence in noise-free conditions, and arousal for recordings captured in-the-wild.