Kenyan man wins top African Innovation prize for App that translates speech to sign language in real-time

A Kenyan entrepreneur who created a web-based app that translates speech into sign language using AI-powered 3D avatars has won a major award for African innovation. Elly Savatia, creator of the app Terp 360, was awarded 50,000 ($67,000) on October 16 by the UKs Royal Academy of Engineering. He won its prestigious Africa Prize for Engineering Innovation, which recognizes technology developed to address challenges on the continent. Savatia's innovation was selected from four finalists across Africa during a ceremony held in Dakar, Senegal.Savatia described his creation as "Google Translate for sign language," explaining that it takes speech and text input and outputs photorealistic avatars signing in real time, allowing users to communicate without relying on human interpreters. He noted that the deaf community in Kenya often struggles to access essential services like education and health care because many professionals do not know sign language. Human interpreters are expensive and scarce, resulting in many deaf people across Africa failing to transition to higher education.  While a government bill was passed earlier this year requiring Kenyan employers to reserve at least 5% of jobs for people with disabilities, Savatia explained that many roles remain inaccessible because companies "cannot afford interpreters" or simply lack the tools to effectively integrate deaf employees. Terp 360 aims to be an "enabler" that can provide sign language translation at scale. Terp 360 was developed in conjunction with deaf and hard-of-hearing Kenyans to record over 2,300 signs, including commonly used phrases and words. Motion sensors were attached to a signer's hands to capture the movements for the AI training. While other avatar-based sign language technologies exist globally, Savatia emphasized that they are often not designed with African sign languages or cultural context in mind. With more than 300 sign languages used worldwide and about 30 in Africa, Terp 360 currently translates from English and Swahili into Kenyan Sign Language. Savatia stated that the app is on track to support Rwandan, Ugandan, South African, British, and American sign languages by mid-2027, with plans to translate from other major African and global languages.  To train the AI in new languages, the developers plan to partner with local NGOs, projects that have visual sign language data sets, and news stations with sign language video archives. They have also established a motion capture studio in Nairobi with the capacity to record and learn 1,000 words a day. Rebecca Enonchong, chair of the prize-judging panel, highlighted the "cutting-edge technology" demonstrated by the solution and its significant social impact, noting that assistive technologies are an underserved area globally. The post Kenyan man wins top African Innovation prize for App that translates speech to sign language in real-time appeared first on Linda Ikeji Blog.