My innovation converts audio recordings of speech in various African languages into equivalent digital text (voice recognition), and generates audio recordings from digital text (speech synthesis). Hardly any commercial voice recognition and speech synthesis software exists for African languages. My innovation allows Africans and speakers of African languages to interact with the Internet and access essential digital services in their native African language.
AJA.LA Studios develops speech technologies that help people who are illiterate and/or live in remote areas access essential services & information.
What problem are you trying to solve?
My innovation provides a means of digitizing African languages in a way that allows speakers of African languages to interact with systems and Internet applications that use a voice-based interface. The most popular example is Internet of Things devices such as personal assistants, e.g. Siri and Alexa, that can accept verbal commands; and web applications that rely on voice requests, e.g. Google Voice Search.
More generally, voice-based interfaces are intuitive and natural, making them accessible to people from a wide range of backgrounds. We see an opportunity to use these speech technologies to help people who may be illiterate and/or live in remote rural areas to access essential digital services that may otherwise be inaccessible to them. We are developing bespoke, proprietary solutions tailored to the African context across healthcare, education, finance, and more.
What is your solution to this problem?
My innovation addresses the need for software that can digitize and “understand” spoken African languages in a way that can be integrated into a wide range of devices and third-party applications. While this software is broadly available in Western contexts and consumer applications such as Siri, we see a clear opportunity to develop software and related applications to serve some of Africa’s most vulnerable populations.
Localized speech technologies, including voice recognition and speech synthesis software, enable Africans and speakers of African languages to access the Internet and digital products using their voice as an interface. We are currently developing voice recognition and speech synthesis software for key African languages, along with proprietary solutions that address challenges posed by illiteracy and inclusion across various modes (mobile, financial, and gender, amongst others).
What is your latest update on your innovation?
I am currently working with partners in two African countries (Nigeria and Rwanda) on private beta projects to expand our prototypes and develop proprietary digital solutions that help address access to essential services in these countries. If successful, the solutions we are developing will have the potential to serve some of the most vulnerable communities in Nigeria and Rwanda, helping millions of people improve their quality of life and giving agency to members of some of the most vulnerable communities by making access to information and services more accessible and natural for them.