Tongue contour tracking and segmentation in lingual ultrasound for speech recognition: A review

K Al-Hammuri, F Gebali, I Thirumarai Chelvan… - Diagnostics, 2022 - mdpi.com
Lingual ultrasound imaging is essential in linguistic research and speech recognition. It has
been used widely in different applications as visual feedback to enhance language learning …

Biosignal-based spoken communication: A survey

T Schultz, M Wand, T Hueber… - … on Audio, Speech …, 2017 - ieeexplore.ieee.org
Speech is a complex process involving a wide range of biosignals, including but not limited
to acoustics. These biosignals-stemming from the articulators, the articulator muscle …

Beyond the edge: Markerless pose estimation of speech articulators from ultrasound and camera images using DeepLabCut

A Wrench, J Balch-Tomes - Sensors, 2022 - mdpi.com
Automatic feature extraction from images of speech articulators is currently achieved by
detecting edges. Here, we investigate the use of pose estimation deep neural nets with …

TaL: a synchronised multi-speaker corpus of ultrasound tongue imaging, audio, and lip videos

MS Ribeiro, J Sanger, JX Zhang… - 2021 IEEE Spoken …, 2021 - ieeexplore.ieee.org
We present the Tongue and Lips corpus (TaL), a multi-speaker corpus of audio, ultrasound
tongue imaging, and lip videos. TaL consists of two parts: TaL1 is a set of six recording …

Multi-hypothesis tracking of the tongue surface in ultrasound video recordings of normal and impaired speech

C Laporte, L Ménard - Medical image analysis, 2018 - Elsevier
Characterizing tongue shape and motion, as they appear in real-time ultrasound (US)
images, is of interest to the study of healthy and impaired speech production. Quantitative …

UltraSuite: a repository of ultrasound and acoustic data from child speech therapy sessions

A Eshky, MS Ribeiro, J Cleland, K Richmond… - arXiv preprint arXiv …, 2019 - arxiv.org
We introduce UltraSuite, a curated repository of ultrasound and acoustic data, collected from
recordings of child speech therapy sessions. This release includes three data collections …

Encoder-decoder CNN models for automatic tracking of tongue contours in real-time ultrasound data

MH Mozaffari, WS Lee - Methods, 2020 - Elsevier
One application of medical ultrasound imaging is to visualize and characterize human
tongue shape and motion in real-time to study healthy or impaired speech production. Due …

Automatic segmentation of speech articulators from real-time midsagittal MRI based on supervised learning

M Labrunie, P Badin, D Voit, AA Joseph, J Frahm… - Speech …, 2018 - Elsevier
Speech production mechanisms can be characterized at a peripheral level by both their
acoustic and articulatory traces along time. Researchers have thus developed very large …

Covert contrast and covert errors in persistent velar fronting

J Cleland, JM Scobbie, C Heyde… - Clinical linguistics & …, 2017 - Taylor & Francis
Acoustic and articulatory studies demonstrate covert contrast in perceptually neutralised
phonemic contrasts in both typical children and children with speech disorders. These covert …

A CNN-based tool for automatic tongue contour tracking in ultrasound images

J Zhu, W Styler, I Calloway - arXiv preprint arXiv:1907.10210, 2019 - arxiv.org
For speech research, ultrasound tongue imaging provides a non-invasive means for
visualizing tongue position and movement during articulation. Extracting tongue contours …