Dynamical model parameters from ultrasound tongue kinematics

TL;DR

This study demonstrates that ultrasound tongue kinematics can reliably estimate parameters of a dynamical speech model, comparable to electromagnetic articulography data, supporting ultrasound as a viable tool for articulatory modeling.

Contribution

It shows that ultrasound imaging can effectively replace EMA for estimating dynamical model parameters in speech articulation analysis.

Findings

Ultrasound and EMA produce comparable dynamical parameters.

Ultrasound captures jaw motion effectively with mandibular tendon tracking.

Ultrasound is a promising alternative for articulatory model evaluation.

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.