Two- way Auslan: Automatic Machine Translation of Australian Sign Language

Project Member(s): Yu, X.

Funding or Partner Organisation: Australian Research Council (ARC Discovery Projects)
Australian Research Council (ARC Discovery Projects)

Start year: 2022

Summary: This project aims to develop a vision-based automatic Auslan machine-translation system between the Auslan (Australian Sign Language) and English language with high accuracy. This will be achieved by researching advanced technologies in computer vision, machine learning and computational language processing. The outcomes of the project will help to break the communication barrier between the deaf and the hearing population, which not only allows the deaf community to access critical information (such as bushfire emergency or epidemic briefing) more easily, but also enables them to communicate with the general hearing population naturally and more freely via the Auslan machine translation system. Significant benefits of the project can be expected, which include 1) to improve the general quality-of-life of Australian deaf community; to alleviate social isolation and to promote a fair, inclusive, and resilient Australian society. Moreover, this project also addresses fundamental science challenges in AI research including video processing, human action, deep learning, digital avatar, linguistic modelling and NLP (natural language processing).

FOR Codes: Knowledge representation and reasoning, Natural language processing, Telehealth, Community health care

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.