On Calibration of Speech Classification Models: Insights from Energy-Based Model Investigations

2024/06/26 by Yaqian Hao, Hao, Yaqian, Chenguang Hu +7 · 1 citation
Computer Science · #Audio and Speech Processing (eess.AS) #FOS: Computer and information sciences #FOS: Electrical engineering #Sound (cs.SD) #Speech Recognition and Synthesis #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2406.18065

openalex publication_date 2024/06/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

For speech classification tasks, deep learning models often achieve high accuracy but exhibit shortcomings in calibration, manifesting as classifiers exhibiting overconfidence. The significance of calibration lies in its critical role in guaranteeing the reliability of decision-making within deep learning systems. This study explores the effectiveness of Energy-Based Models in calibrating confidence for speech classification tasks by training a joint EBM integrating a discriminative and a generative model, thereby enhancing the classifiers calibration and mitigating overconfidence. Experimental evaluations conducted on three speech classification tasks specifically: age, emotion, and language recognition. Our findings highlight the competitive performance of EBMs in calibrating the speech classification models. This research emphasizes the potential of EBMs in speech classification tasks, demonstrating their ability to enhance calibration without sacrificing accuracy.

Cited by

• Non-native Children's Automatic Speech Assessment Challenge (NOCASA)

Related

• Testing Correctness, Fairness, and Robustness of Speech Emotion Recognition Models
• HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models
• Reducing Bias in Production Speech Models
• Classification errors distort findings in automated speech processing: examples and solutions from child-development research
• Automatic Learning of Subword Dependent Model Scales