Bridging Modalities: Knowledge Distillation and Masked Training for Translating Multi-Modal Emotion Recognition to Uni-Modal, Speech-Only Emotion Recognition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Muaz, Muhammad, Paull, Nathan, Malagavalli, Jahnavi
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914631709097984
author Muaz, Muhammad
Paull, Nathan
Malagavalli, Jahnavi
author_facet Muaz, Muhammad
Paull, Nathan
Malagavalli, Jahnavi
contents This paper presents an innovative approach to address the challenges of translating multi-modal emotion recognition models to a more practical and resource-efficient uni-modal counterpart, specifically focusing on speech-only emotion recognition. Recognizing emotions from speech signals is a critical task with applications in human-computer interaction, affective computing, and mental health assessment. However, existing state-of-the-art models often rely on multi-modal inputs, incorporating information from multiple sources such as facial expressions and gestures, which may not be readily available or feasible in real-world scenarios. To tackle this issue, we propose a novel framework that leverages knowledge distillation and masked training techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2401_03000
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bridging Modalities: Knowledge Distillation and Masked Training for Translating Multi-Modal Emotion Recognition to Uni-Modal, Speech-Only Emotion Recognition
Muaz, Muhammad
Paull, Nathan
Malagavalli, Jahnavi
Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
This paper presents an innovative approach to address the challenges of translating multi-modal emotion recognition models to a more practical and resource-efficient uni-modal counterpart, specifically focusing on speech-only emotion recognition. Recognizing emotions from speech signals is a critical task with applications in human-computer interaction, affective computing, and mental health assessment. However, existing state-of-the-art models often rely on multi-modal inputs, incorporating information from multiple sources such as facial expressions and gestures, which may not be readily available or feasible in real-world scenarios. To tackle this issue, we propose a novel framework that leverages knowledge distillation and masked training techniques.
title Bridging Modalities: Knowledge Distillation and Masked Training for Translating Multi-Modal Emotion Recognition to Uni-Modal, Speech-Only Emotion Recognition
topic Sound
Artificial Intelligence
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2401.03000