Grant: Alliance Grants
École de technologie supérieure
$25,000.00
Palate shape analysis from 3D ultrasound images of the vocal tract
FY 2023-24
Summary
Ultrasound (US) imaging is ideally suited for studying tongue shape and motion during speech. 2D US images are widely used for this purpose, and many methodological tools are being developed by the phonetics community to extract and characterize tongue shape from these. Recently, 3D US imaging has emerged as a more powerful modality to study speech articulation (Lulich, 2018, 2019) by allowing visualization of nearly the entire 3D surface of the tongue. As such, it has strong potential for deepening our understanding of tongue motion during speech. We recently initiated a collaboration with S. Lulich and developed a reliable automated tool to extract tongue surfaces from 3D US vocal tract images. The proposed project aims to expand on the initial collaboration with S. Lulich to develop tools to extract and characterize the surface of the palate and, more generally, oral cavity shape, from 3D US images of the vocal tract. This will help understand how tongue and palate shapes interact in the production of speech, and could inform new strategies for speech therapy. One Master's student and two undergraduate interns will be trained in this multidisciplinary project, and will be involved in the development and validation of the image segmentation, image registration and shape characterization tools required for palate shape extraction and characterization from 3D US data. The new tools will build on previous work by my team on the extraction of palate shape in 2D US data, as well as our recent work with S. Lulich on tongue surface extraction from 3D US data. This project will lead to important methodological advances in the field of articulatory phonetics, with potential applications to the treatment of articulatory difficulties in speech therapy. The development of 3D ultrasound vocal tract image analysis expertise on Canadian soil would position Canada as a leader in the development of such applications and would also facilitate the adoption of 3D US technology, with all its benefits, in Canadian phonetics research laboratories.
Program
Alliance Grants
Recipient
Location
Quebec, Canada
Recipient Type
Academia
Type
Grant
Source
NSERC's Awards Data
As published
Application id
580955-2022
Name nom
Laporte, Catherine C
Department département
Génie électrique
Organization id
53
Institution établissement
École de technologie supérieure
Province en
Québec
Province fr
Québec
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2023
Competition year année de concours
2022
Award amount
25000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
1101
Area of application group en
Health, education and social services
Area of application group fr
Santé publique, éducation et services sociaux
Area of application en
Human health (including medically-related psychological research)
Area of application fr
Santé publique (y compris recherche psychologique liée à la médecine)
Research subject code
1901
Research subject group en
Biomedical engineering
Research subject group fr
Biomedical technology
Research subject en
Génie biomédical
Research subject fr
Technologie biomédicale
Application title
Palate shape analysis from 3D ultrasound images of the vocal tract
Keyword
3D ultrasound imaging; Articulatory phonetics; Image segmentation; Shape analysis; Surface registration
Application summary
Ultrasound (US) imaging is ideally suited for studying tongue shape and motion during speech. 2D US images are widely used for this purpose, and many methodological tools are being developed by the phonetics community to extract and characterize tongue shape from these. Recently, 3D US imaging has emerged as a more powerful modality to study speech articulation (Lulich, 2018, 2019) by allowing visualization of nearly the entire 3D surface of the tongue. As such, it has strong potential for deepening our understanding of tongue motion during speech. We recently initiated a collaboration with S. Lulich and developed a reliable automated tool to extract tongue surfaces from 3D US vocal tract images. The proposed project aims to expand on the initial collaboration with S. Lulich to develop tools to extract and characterize the surface of the palate and, more generally, oral cavity shape, from 3D US images of the vocal tract. This will help understand how tongue and palate shapes interact in the production of speech, and could inform new strategies for speech therapy. One Master's student and two undergraduate interns will be trained in this multidisciplinary project, and will be involved in the development and validation of the image segmentation, image registration and shape characterization tools required for palate shape extraction and characterization from 3D US data. The new tools will build on previous work by my team on the extraction of palate shape in 2D US data, as well as our recent work with S. Lulich on tongue surface extraction from 3D US data. This project will lead to important methodological advances in the field of articulatory phonetics, with potential applications to the treatment of articulatory difficulties in speech therapy. The development of 3D ultrasound vocal tract image analysis expertise on Canadian soil would position Canada as a leader in the development of such applications and would also facilitate the adoption of 3D US technology, with all its benefits, in Canadian phonetics research laboratories.