The University of Ghana, in partnership with Google Research Africa and UCL’s Global Disability Innovation Hub (GDI Hub), has launched an innovative AI initiative called “tɛkyerɛma pa” (which translates to “Good Tongue”). The project is designed to improve communication for individuals with non-standard speech patterns, which are often caused by conditions such as cerebral palsy, ALS, stroke, Down syndrome, or Parkinson’s disease. It aims to enhance AI-powered speech recognition for five key Ghanaian languages: Akan, Ewe, Ikposo, Dagbani, and Dagaare. This initiative is a significant step toward ensuring that speech recognition technology is more inclusive and accessible to all Ghanaians, including those with diverse speech patterns.
In many cases, speech recognition systems struggle to accurately understand individuals with non-standard speech, making it difficult for them to use digital devices effectively. The tɛkyerɛma pa project seeks to bridge this gap by training AI models to recognize and interpret these speech patterns, particularly in local Ghanaian languages. The ultimate goal is to improve accessibility for individuals who are currently underserved by existing speech recognition technologies. This project is being led by Professor Isaac Wiafe, an Associate Professor at the University of Ghana, who emphasized that the initiative aims to ensure no one is left behind in the advancement of technology. With this project, more Ghanaians, regardless of their speech patterns, will be able to communicate more effectively.
The project is backed by a $40,000 grant from Google, and the research is being supported by UCL’s GDI Hub through the AT2030 program. Katrin Tomanek, a Senior Research Scientist at Google Research, expressed her excitement about the collaboration, noting that the project would create the first open-source dataset of non-standard speech in Ghanaian languages. This initiative aligns with Google’s commitment to fostering AI research in Africa and ensuring that advancements in technology benefit all individuals, regardless of their speech. Professor Cathy Holloway, Academic Director of the GDI Hub, also highlighted the importance of expanding AI-powered speech recognition to a wider array of languages. She believes this will allow people with non-standard speech to communicate better with others and interact more efficiently with technology in their daily lives.
The success of this initiative has the potential to make a significant impact on the lives of people with speech impairments in Ghana, as well as in other parts of Africa. By focusing on local languages, the project promotes inclusivity and accessibility, ensuring that AI technology is not just an international tool but one that can be tailored to meet the unique needs of different communities. The collaboration between the University of Ghana, Google, and the GDI Hub sets a powerful precedent for how technology can be harnessed to solve real-world challenges and improve lives. With further development, this project could serve as a model for similar initiatives across the continent.
blogpay
Total Comments: 0