Leveraging Unlabeled Audio-Visual Data in Speech Emotion Recognition using Knowledge Distillation

TL;DR

This paper introduces LightweightSER, a knowledge distillation framework that utilizes unlabeled audio-visual data to improve speech emotion recognition, reducing reliance on large labeled datasets.

Contribution

It presents a novel knowledge distillation approach that leverages unlabeled multi-modal data for SER using large teacher models to train lightweight student models.

Findings

LiSER achieves competitive accuracy on RAVDESS and CREMA-D datasets.

The framework reduces the need for extensive labeled data in SER.

Lightweight models trained with LiSER outperform baseline models.

Abstract

Voice interfaces integral to the human-computer interaction systems can benefit from speech emotion recognition (SER) to customize responses based on user emotions. Since humans convey emotions through multi-modal audio-visual cues, developing SER systems using both the modalities is beneficial. However, collecting a vast amount of labeled data for their development is expensive. This paper proposes a knowledge distillation framework called LightweightSER (LiSER) that leverages unlabeled audio-visual data for SER, using large teacher models built on advanced speech and face representation models. LiSER transfers knowledge regarding speech emotions and facial expressions from the teacher models to lightweight student models. Experiments conducted on two benchmark datasets, RAVDESS and CREMA-D, demonstrate that LiSER can reduce the dependence on extensive labeled datasets for SER tasks.