Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Engage Plus Grants Program

Acadia University

$12,500.00

Improved automatic pronunciation feedback for English learners, with focus on prosodic correction

EF 2016-17

Résumé
Fundy Language Analytics, Inc. is a young Nova Scotia company which is developing a novel software product to help language students learn English. The primary goal of the product is to supplement the one-on-one learning of the student by providing speech exercises with automated feedback. The previous Engage project with Dr. Mendivil focused on detecting and highlighting words which are pronounced incorrectly. This lead to an approach now being implemented to help score the phonemic pronunciation error of English learners.With the improvement in the reliability of phonemic error detection it has become clear that a robust tool must also evaluate and correct prosodic errors, which are at least as important as phonemic errors for verbal fluency. Prosodic errors are typically split into three categories: intonation (the pitch changes of the speech), rhythm (the timing of various syllables), and stress (the emphasis of various syllables). These errors are much more difficult to detect, and even when detected, it is difficult to display adequate feedback to a learner in order to make it obvious how the learner might improve. In this project, we will investigate mechanisms to detect, correct, and display feedback for these types of errors.
Programme
Engage Plus Grants Program
Bénéficiaire
Emplacement
Nova Scotia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
501557-2016
Name nom
Mendivil, Franklin
Department département
Mathematics and Statistics
Organization id
78
Institution établissement
Acadia University
Province en
Nova Scotia
Province fr
Nouvelle-Écosse
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2016
Competition year année de concours
2016
Award amount
12500
Program id
EGP2
Program name en
Engage Plus Grants Program
Program name fr
Programme de subvention d'engagement partenarial Plus
Group en
Research partnerships programs
Group fr
Programmes de partenariat
Committee code
1551
Committee name en
Atlantic Internal Decision Committee
Committee name fr
Comité de décision interne pour l'Atlantique
Area of application code
801
Area of application group en
Information and communication services
Area of application group fr
Services d'information et de télécommunications
Area of application en
Computer software
Area of application fr
Logiciel
Research subject code
2801
Research subject group en
Artificial intelligence
Research subject group fr
Intelligence artificielle
Research subject en
Natural language and speech understanding
Research subject fr
Langage naturel et reconnaissance de la parole
Partie
1
Nb partie
1
Application title
Improved automatic pronunciation feedback for English learners, with focus on prosodic correction
Keyword
NSERC
Application summary
Fundy Language Analytics, Inc. is a young Nova Scotia company which is developing a novel software product to help language students learn English. The primary goal of the product is to supplement the one-on-one learning of the student by providing speech exercises with automated feedback. The previous Engage project with Dr. Mendivil focused on detecting and highlighting words which are pronounced incorrectly. This lead to an approach now being implemented to help score the phonemic pronunciation error of English learners.With the improvement in the reliability of phonemic error detection it has become clear that a robust tool must also evaluate and correct prosodic errors, which are at least as important as phonemic errors for verbal fluency. Prosodic errors are typically split into three categories: intonation (the pitch changes of the speech), rhythm (the timing of various syllables), and stress (the emphasis of various syllables). These errors are much more difficult to detect, and even when detected, it is difficult to display adequate feedback to a learner in order to make it obvious how the learner might improve. In this project, we will investigate mechanisms to detect, correct, and display feedback for these types of errors.