Building a Gender-Bias-Resistant Super Corpus as a Deep Learning Baseline for Speech Emotion Recognition
Sensors · 22.03.2025 · 25 (7) · 1991
DOI: 10.3390/s25071991 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 22.03.2025. Verfasst von Babak Abbaschian und 1 weiteren Autor:innen. Beteiligte Einrichtung: Computer Science and Engineering Department, University of Louisville, Louisville, KY 40292, USA. Hauptthemen laut MEDLINE: Deep Learning, Emotions, Speech. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The focus on Speech Emotion Recognition has dramatically increased in recent years, driven by the need for automatic speech-recognition-based systems and intelligent assistants to enhance user experience by incorporating emotional content. While deep learning techniques have significantly advanced SER systems, their robustness concerning speaker gender and out-of-distribution data has not been thoroughly examined. Furthermore, standards for SER remain rooted in landmark papers from the 2000s, even though modern deep learning architectures can achieve comparable or superior results to the state of the art of that era. In this research, we address these challenges by creating a new super corpus from existing databases, providing a larger pool of samples. We benchmark this dataset using various deep learning architectures, setting a new baseline for the task. Additionally, our experiments reveal that models trained on this super corpus demonstrate superior generalization and accuracy and exhibit lower gender bias compared to models trained on individual databases. We further show that traditional preprocessing techniques, such as denoising and normalization, are insufficient to address inherent biases in the data. However, our data augmentation approach effectively shifts these biases, improving model fairness across gender groups and emotions and, in some cases, fully debiasing the models.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Computer Science and Engineering Department, University of Louisville, Louisville, KY 40292, USA.
ORCID-Profile: Adel Elmaghraby
Zitieren
APA
Abbaschian, B., & Elmaghraby, A. (2025). Building a Gender-Bias-Resistant Super Corpus as a Deep Learning Baseline for Speech Emotion Recognition. Sensors, 25(7), 1991. https://doi.org/10.3390/s25071991
Vancouver
Abbaschian B, Elmaghraby A. Building a Gender-Bias-Resistant Super Corpus as a Deep Learning Baseline for Speech Emotion Recognition. Sensors. 2025;25(7):1991. doi:10.3390/s25071991
BibTeX
@article{Abbaschian2025,
author = {Abbaschian, Babak and Elmaghraby, Adel},
title = {Building a Gender-Bias-Resistant Super Corpus as a Deep Learning Baseline for Speech Emotion Recognition},
journal = {Sensors},
year = {2025},
volume = {25},
number = {7},
pages = {1991},
doi = {10.3390/s25071991}
}
EUVIMED