Saved in:
Bibliographic Details
Main Authors: Hallmen, Tobias, Deuser, Fabian, Oswald, Norbert, André, Elisabeth
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2403.11879
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911918945468416
author Hallmen, Tobias
Deuser, Fabian
Oswald, Norbert
André, Elisabeth
author_facet Hallmen, Tobias
Deuser, Fabian
Oswald, Norbert
André, Elisabeth
contents In this research, we introduce a novel methodology for assessing Emotional Mimicry Intensity (EMI) as part of the 6th Workshop and Competition on Affective Behavior Analysis in-the-wild. Our methodology utilises the Wav2Vec 2.0 architecture, which has been pre-trained on an extensive podcast dataset, to capture a wide array of audio features that include both linguistic and paralinguistic components. We refine our feature extraction process by employing a fusion technique that combines individual features with a global mean vector, thereby embedding a broader contextual understanding into our analysis. A key aspect of our approach is the multi-task fusion strategy that not only leverages these features but also incorporates a pre-trained Valence-Arousal-Dominance (VAD) model. This integration is designed to refine emotion intensity prediction by concurrently processing multiple emotional dimensions, thereby embedding a richer contextual understanding into our framework. For the temporal analysis of audio data, our feature fusion process utilises a Long Short-Term Memory (LSTM) network. This approach, which relies solely on the provided audio data, shows marked advancements over the existing baseline, offering a more comprehensive understanding of emotional mimicry in naturalistic settings, achieving the second place in the EMI challenge.
format Preprint
id arxiv_https___arxiv_org_abs_2403_11879
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Unimodal Multi-Task Fusion for Emotional Mimicry Intensity Prediction
Hallmen, Tobias
Deuser, Fabian
Oswald, Norbert
André, Elisabeth
Sound
Artificial Intelligence
Audio and Speech Processing
In this research, we introduce a novel methodology for assessing Emotional Mimicry Intensity (EMI) as part of the 6th Workshop and Competition on Affective Behavior Analysis in-the-wild. Our methodology utilises the Wav2Vec 2.0 architecture, which has been pre-trained on an extensive podcast dataset, to capture a wide array of audio features that include both linguistic and paralinguistic components. We refine our feature extraction process by employing a fusion technique that combines individual features with a global mean vector, thereby embedding a broader contextual understanding into our analysis. A key aspect of our approach is the multi-task fusion strategy that not only leverages these features but also incorporates a pre-trained Valence-Arousal-Dominance (VAD) model. This integration is designed to refine emotion intensity prediction by concurrently processing multiple emotional dimensions, thereby embedding a richer contextual understanding into our framework. For the temporal analysis of audio data, our feature fusion process utilises a Long Short-Term Memory (LSTM) network. This approach, which relies solely on the provided audio data, shows marked advancements over the existing baseline, offering a more comprehensive understanding of emotional mimicry in naturalistic settings, achieving the second place in the EMI challenge.
title Unimodal Multi-Task Fusion for Emotional Mimicry Intensity Prediction
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2403.11879