Collection and transcription of a corpus of aphasic speech for the development of a prototype of an intelligent communication aid application

Aphasia is an impairment of language caused by an injury to the brain. Word finding difficulties often accompany aphasia and can persist even after intensive speech therapy, having a negative impact on the person’s social participation and quality of life. Today’s communication aids can improve the ability to effectively communicate but findings from focus groups that we have held show a need for a more intelligent and intuitive communication aid that will better meet individuals’ needs. Our ultimate goal is to develop a prototype of an intelligent communication aid application that will target these unmet needs. However, training the machine learning algorithm that will power such an application will require large quantities of aphasic speech data that are not currently available. In this project, we will begin by collecting a corpus of speech output of people with aphasia. Then we will phonetically transcribe this output. These two forms of the data will then be used to train the prototype that we will de

Faculty Supervisor:

Gonia Jarema;Eva Kehayia;Eva Kehayia;Gonia Jarema

Student:

Partner:

IBM Canada Ltd;IBM Europe (France)

Discipline:

Life Sciences

Sector:

Information and cultural industries; Manufacturing; Professional, scientific and technical services

University:

McGill University; Université de Montréal

Program: