Movement Detection of Tongue and Related Body Parts Using IR-UWB Radar

TL;DR

This paper explores using IR-UWB radar to detect tongue and related body part movements for silent speech interfaces, achieving high accuracy in classifying movement states without contact.

Contribution

It introduces a novel method combining feature extraction and GMM-HMM for classifying tongue movements using IR-UWB radar.

Findings

Achieved at least 90% accuracy in classifying tongue movement states.

Demonstrated feasibility of IR-UWB radar for silent speech interface development.

Abstract

Because an impulse radio ultra-wideband (IR-UWB) radar can detect targets with high accuracy, work through occluding materials, and operate without contact, it is an attractive hardware solution for building silent speech interfaces, which are non-audio-based speech communication devices. As tongue movement is strongly engaged in pronunciation, detecting its movement is crucial for developing silent speech interfaces. In this study, we attempted to classify the motionless and moving states of an invisible tongue and its related body parts using an IR-UWB radar whose antennas were pointed toward the participant's chin. Using the proposed feature extraction algorithm and a Gaussian mixture model - hidden Markov model, we classified two states of the invisible tongue of four individual participants with a minimum accuracy of 90%.