What Does it Take to Generalize SER Model Across Datasets? A Comprehensive Benchmark
Ibrahim, Adham
Ibrahim, Adham
Author
Supervisor
Department
Machine Learning
Embargo End Date
2026-05-21
Type
Thesis
Date
2024
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Speech emotion recognition (SER) is essential for enhancing human-computer interaction in speech-based applications. Despite improvements in specific emotional datasets, there is still a research gap in SER s capability to generalize across real-world situations. In this paper, we investigate approaches to generalize the SER system across different emotion datasets. In particular, incorporate 11 emotional speech datasets and illustrate a comprehensive benchmark on the SER task. We also address the challenge of imbalanced data distribution using oversampling methods when combining SER datasets for training. Furthermore, we explore various evaluation protocols for adeptness in the generalization of SER. Building on this, we explore the potential of Whisper for SER, emphasizing the importance of thorough evaluation. Our approach is designed to advance SER technology by integrating speaker-independent methods.
Citation
A. Ibrahim, What Does it Take to Generalize SER Model Across Datasets? A Comprehensive Benchmark, MS. Thesis, Machine Learning, MBZUAI, Abu Dhabi, UAE, 2024