Dynamical model parameters from ultrasound tongue kinematics

2025-10-21

AI Summary

Traditional articulatory dynamics modeling relies on invasive or costly measurement techniques, limiting clinical and developmental applications. Method: This study investigates whether ultrasound-based tongue kinematics can reliably estimate parameters of a linear resonant oscillator model—specifically damping ratio and natural frequency—and validates these estimates against concurrently acquired electromagnetic articulography (EMA) data. Using synchronized ultrasound and EMA recordings, we modeled tongue body and mandibular short tendon movements during speech production. Contribution/Results: Ultrasound-derived parameter estimates exhibit excellent agreement with EMA (ICC > 0.85) and accurately capture dynamic articulatory behavior. To our knowledge, this is the first empirical demonstration that ultrasound imaging can serve as a noninvasive, cost-effective alternative for articulatory dynamics modeling. The findings broaden methodological options in speech physiology research and provide a novel, noninvasive framework for dynamical analysis in clinical assessment and language acquisition studies.

Technology Category

• Natural Language Processing: Speech
• Cognitive Modeling & Cognitive Systems: Simulating Human Behavior
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution

Abstract

The control of speech can be modelled as a dynamical system in which articulators are driven toward target positions. These models are typically evaluated using fleshpoint data, such as electromagnetic articulography (EMA), but recent methodological advances make ultrasound imaging a promising alternative. We evaluate whether the parameters of a linear harmonic oscillator can be reliably estimated from ultrasound tongue kinematics and compare these with parameters estimated from simultaneously-recorded EMA data. We find that ultrasound and EMA yield comparable dynamical parameters, while mandibular short tendon tracking also adequately captures jaw motion. This supports using ultrasound kinematics to evaluate dynamical articulatory models.

Problem

• Estimating dynamical model parameters from ultrasound tongue kinematics
• Comparing ultrasound-derived parameters with EMA data reliability
• Validating ultrasound as alternative for articulatory model evaluation

Innovation

• Ultrasound tongue kinematics estimates dynamical model parameters
• Compares ultrasound parameters with EMA-derived parameters
• Mandibular tracking captures jaw motion in articulatory models