🤖 AI Summary
This study investigates the neurophysiological mechanisms underlying preschool stuttering, focusing on speech-motor control deficits and context-dependent autonomic arousal (e.g., heart rate, electrodermal activity) as modulators of speech fluency. To address this, we propose a physiology-informed dynamic importance modeling framework for speech, implemented via a novel hypernetwork architecture that enables cross-modal temporal alignment between acoustic features and multimodal physiological signals. The model incorporates a physiology-driven attention mechanism and end-to-end streaming feature extraction. Critically, it yields the first interpretable, real-world “fluent speech–motor control factor” mapping model. Evaluated on a dataset of 73 preschool-aged children (stuttering and typically fluent), our approach significantly outperforms state-of-the-art baselines in accuracy, latency, robustness to signal noise, and subject-specific adaptability. The resulting interpretable biomarkers hold direct translational potential for early, objective, and personalized stuttering intervention.
📝 Abstract
This paper presents a novel approach named PASAD that detects changes in perceptually fluent speech acoustics of young children. Particularly, analysis of perceptually fluent speech enables identifying the speech-motor-control factors that are considered as the underlying cause of stuttering disfluencies. Recent studies indicate that the speech production of young children, especially those who stutter, may get adversely affected by situational physiological arousal. A major contribution of this paper is leveraging the speaker's situational physiological responses in real-time to analyze the speech signal effectively. The presented PASAD approach adapts a Hyper-Network structure to extract temporal speech importance information leveraging physiological parameters. Moreover, we collected speech and physiological sensing data from 73 preschool-age children who stutter (CWS) and who do not stutter (CWNS) in different conditions. PASAD's unique architecture enables identifying speech attributes distinct to a CWS's fluent speech and mapping them to the speaker's respective speech-motor-control factors. Extracted knowledge can enhance understanding of children's speech-motor-control and stuttering development. Our comprehensive evaluation shows that PASAD outperforms state-of-the-art multi-modal baseline approaches in different conditions, is expressive and adaptive to the speaker's speech and physiology, generalizable, robust, and is real-time executable.
