$40,000 project on non-standard speech patterns commences
The University of Ghana (UG), Google Research Africa, and University College of London’s (UCL) Global Disability Innovation Hub (GDI Hub) have collaborated on “t3kyer3ma pa” (“Good Tongue”), an AI-based initiative, to improve communication for individuals with non-standard speech patterns in Ghana.
The ‘t3kyer3ma pa’ project also aims to address the gap faced by many individuals with non-standard speech due to conditions like cerebral palsy, ALS, stroke, down syndrome, or Parkinson disease.
Project ‘t3kyer3ma pa’ supported with a $40,000 grant from Google and research expertise from UCL’s GDI Hub provided through the AT2030 programme, which is as assistive technology.
At media briefing in Accra on Friday, Professor Isaac Wiafe, Project Lead, and an Associate Professor, UG, said the project, which was focused on improving AI-powered speech recognition technology for five major Ghanaian languages, was a significant step in making communication more inclusive for all.
The five Ghanaian languages are Akan, Ewe, Ikposo, Dagaare and Dagbani.
Prof. Wiafe explained that current speech recognition technologies often struggled to accurately interpret non-standard speech, limiting their effectiveness.
He said that, “we are training AI models to better understand these speech patterns in local languages, ultimately enhancing accessibility and making speech recognition more accessible to Ghanaians with non-standard speech.”
Prof. Waife further explained that, “we are thrilled to lead this important initiative, which reflects our commitment to using technology to solve real-world challenges. By developing localised AI solutions, we can ensure that more Ghanaians have the opportunity to communicate effectively, regardless of their speech patterns.”
A Senior Research Scientist, Google Research, Katrin Tomanek, underlined that the project reflected Google’s ongoing commitment to supporting AI research in Africa, and ensuring that technological advances benefited everyone, regardless of how they speak.
She said the project builds on continuous research in making Automatic Speech Recognition (ASR) more accessible with the hope of using the insights learnt from work of the project Euphonia to help local researchers create ASR models for local languages.
Academic Director, GDI Hub, Prof. Cathy Hollowaya, said expanding the reach of AI-powered recognition to more languages was crucial to ensure people living with non-standard speech can communicate more effectively with people and devices in their daily lives.
She also stated that the collaboration will not only benefit individuals in Ghana, but also provide valuable insights for global AI development, adding that it will lay the foundation for future language models and collection in Africa.
Prof. Hollowaya said the initiative was part of Google’s broader commitment to advancing AI development in Africa.
By providing funding, technical expertise, and cloud computing resources, she said Google aimed at fostering an ecosystem where local researchers could lead innovations that addressed both local and global challenges.
BY JEMIMA ESINAM
KUATSINU