A proposed artificial intelligence-based real-time speech-to-text to sign language translator for South African official languages for the COVID-19 era and beyond: In pursuit of solutions for the hearing impaired.
Milka C Madahana, Katijah Khoza-Shangase, Nomfundo Moroe and 3 others
PMID 36073078WHAT IT FOUND
A scoping review found almost no evidence for real-time AI speech-to-sign-language tools in African languages.
Existing tools are mostly conceptual or English-only. Clinicians cannot rely on current technology to bridge communication gaps for non-English speaking deaf or hard-of-hearing patients.
Key findings
01The review identified only six relevant studies, with just one implemented tool (Deaf Chat) that targets English-speaking South Africans, while the rest were conceptual or from other regions.
02There is a significant lack of evidence for AI-based real-time speech-to-text to sign language translation for African languages, with most existing technology catering only to English speakers.
03Current assistive technologies like real-time captioning are limited by language and accent, failing to support the diverse linguistic landscape of South Africa where English is a home language for less than 10% of the population.
STILL TO COME
How it was doneWhat they foundWhat it means for SLPs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The review only included studies published in English between 2019 and 2021, potentially missing relevant work in other languages or earlier periods. The search yielded only six final studies, indicating a very small evidence base. The review is a scoping review and does not assess the quality or efficacy of the identified tools, only their existence and stage of development. The proposed implementation plan for new tools is theoretical and has not been tested or validated in this paper.
Declared interests
The authors declared no conflicts of interest. The study was conducted without direct contact with human or animal subjects.
The easy way to misread this
Do not interpret the proposed implementation plan or the existence of the 'Deaf Chat' prototype as evidence that functional, accessible AI translation tools are currently available for South African languages. The review explicitly states there is a 'dearth of evidence' and that existing tools are limited to English or are conceptual.