Relationship between objective and subjective perceptual measures of speech in individuals with head and neck cancer

2025-07-28

AI Summary

This study investigates the relationship between subjective perceptual assessments and objective acoustic measurements of speech in head and neck cancer (HNC) patients. Using a large-scale clinical speech dataset, trained listeners provided multidimensional subjective ratings of intelligibility, articulation, and voice quality, while concurrent acoustic analyses quantified speech rate, spectral features, and temporal characteristics. Results revealed high inter-correlation among the three subjective dimensions (r > 0.8), suggesting shared underlying pathophysiological mechanisms; intelligibility ratings showed significant associations with multiple objective metrics—including speech intelligibility index, speaking rate, and fundamental frequency stability (p < 0.001). The key contribution is the first empirical demonstration that intelligibility alone robustly captures overall speech function in HNC patients post-radiotherapy or chemotherapy, establishing it as a concise, reliable, and clinically feasible core metric for speech rehabilitation monitoring.

Technology Category

• Natural Language Processing: Speech
• Machine Learning: Evaluation and Analysis
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Security and Privacy: Large-scale security measurements

Abstract

Meaningful speech assessment is vital in clinical phonetics and therapy monitoring. This study examined the link between perceptual speech assessments and objective acoustic measures in a large head and neck cancer (HNC) dataset. Trained listeners provided ratings of intelligibility, articulation, voice quality, phonation, speech rate, nasality, and background noise on speech. Strong correlations were found between subjective intelligibility, articulation, and voice quality, likely due to a shared underlying cause of speech symptoms in our speaker population. Objective measures of intelligibility and speech rate aligned with their subjective counterpart. Our results suggest that a single intelligibility measure may be sufficient for the clinical monitoring of speakers treated for HNC using concomitant chemoradiation.

Problem

• Link between perceptual and acoustic speech measures in HNC
• Correlation of subjective intelligibility with objective speech metrics
• Clinical utility of single intelligibility measure for HNC monitoring

Innovation

• Correlates subjective and objective speech measures
• Uses trained listeners for perceptual ratings
• Proposes single intelligibility measure for monitoring