# Dynamical model parameters from ultrasound tongue kinematics

arXiv: https://arxiv.org/abs/2510.18629 · HTML: https://mlsanity.com/paper/2510.18629/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 26 references that are in the map.
- First posted on arXiv 21 Oct 2025.

## Builds on (most cited first, 6 of 6)

- [Markerless tracking of user-defined features with deep learning](https://mlsanity.com/paper/1804.03142/) (2018)
- [A unified sparse optimization framework to learn parsimonious physics-informed models from data](https://mlsanity.com/paper/1906.10612/) (2019)
- [Towards a dynamical model of English vowels. Evidence from diphthongisation](https://mlsanity.com/paper/2409.00275/) (2024)
- [Scaling laws for nonlinear dynamical models of articulatory control](https://mlsanity.com/paper/2411.12720/) (2024)
- [Nonlinear second-order dynamics describe labial constriction trajectories across languages and contexts](https://mlsanity.com/paper/2410.08351/) (2024)
- [Discovering dynamical laws for speech gestures](https://mlsanity.com/paper/2504.04849/) (2025)

## Built on by (most cited first, 2 of 2)

- [AURORA Model of Formant-to-Tongue Inversion for Didactic and Clinical Applications](https://mlsanity.com/paper/2603.17543/) (2026)
- [Articulatory strategy as a source of variation in acoustic vowel dynamics](https://mlsanity.com/paper/2605.23416/) (2026)

## Abstract (arXiv)

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.