The 2D+ Dynamic Articulatory Model DYNARTmo: Tongue-Palate Contact Area Estimation

2025-08-10

AI Summary

This study addresses the challenge of accurately estimating tongue–palate contact regions from two-dimensional (2D) mid-sagittal tongue contours. We propose an analytical method integrating three-dimensional (3D) hard-palate geometric modeling. Within the DYNARTmo dynamic articulation framework, we implement— for the first time under a 2D+ paradigm—explicit computation of tongue–palate contact areas. Two coronal-plane curvature models—semi-elliptical and cosine-based—are employed to infer lateral contact points from the mid-sagittal tongue contour, enabling synchronized static and dynamic articulatory visualization. Innovatively, we integrate coordinated animations across sagittal, laryngeal, and palatal views, generating electropalatography-like (EPG-like) output. The method delivers an interpretable, animatable, and multi-view quantitative analysis tool, advancing research on speech production mechanisms, clinical diagnosis of articulatory disorders, and pedagogical applications in speech therapy and phonetics education.

Technology Category

Natural Language Processing: SpeechComputer Vision: Language and VisionMachine Learning: Evaluation and Analysis

Application Category

Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphsUser Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systemsWeb Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

This paper describes an extension of the two-dimensional dynamic articulatory model DYNARTmo by integrating an internal three-dimensional representation of the palatal dome to estimate tongue-palate contact areas from midsagittal tongue contours. Two alternative dome geometries - a half-ellipse and a cosine based profile - are implemented to model lateral curvature in the coronal plane. Using these geometries, lateral contact points are analytically computed for each anterior-posterior position, enabling the generation of electropalatography-like visualizations within the 2D+ framework. The enhanced model supports three synchronized views (sagittal, glottal, and palatal) for static and dynamic (animated) articulation displays, suitable for speech science education and speech therapy. Future work includes adding a facial (lip) view and implementing articulatory-to-acoustic synthesis to quantitatively evaluate model realism.

Problem

• Estimates tongue-palate contact areas from tongue contours
• Models lateral curvature with two dome geometries
• Generates electropalatography-like visualizations in 2D+ framework

Innovation

• 3D palatal dome for tongue-palate contact estimation
• Analytical lateral contact points computation
• Synchronized multi-view articulation displays