Year: 2022
Type: conference-paper
Abstract: In this paper, we introduce a pretrained audio-visual Transformer trained on more than 500k utterances from nearly 4000 celebrities from the VoxCeleb2 dataset for human behavior understanding. The model aims to capture and extract useful information from the interactions between human facial and auditory behaviors, with application in emotion recognition. We evaluate the model performance on two datasets, namely CREMAD-D (emotion classification) and MSP-IMPROV (continuous emotion regression). Experimental results show that fine-tuning the pre-trained model helps improving emotion classification accuracy by 5-7% and Concordance Correlation Coefficients (CCC) in continuous emotion recognition by 0.03-0.09 compared to the same model trained from scratch. We also demonstrate the robustness of finetuning the pre-trained model in a low-resource setting. With only 10% of the original training set provided, finetuning the pre-trained model can lead to at least 10% better emotion recognition accuracy and a CCC score improvement by at least 0.1 for continuous emotion recognition.
Authors: Minh Tran, Mohammad Soleymani
Institution: University of Southern California
Language: English
Topic: Emotion and Mood Recognition
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funders: Arm, Army Research Office
Awards: G2608336305, G486694964, G7452299184
OpenAlex ID: W4225959162