How we got here

GDI Hub’s Centre for Digital Language Inclusion (CDLI) co-creation sesison

As part of this journey, a co-creation workshop, hosted at Kenya Institute of Special Education (KISE), brought together participants, mentors, and facilitators for a full day of collaboration on inclusive Automatic Speech Recognition (ASR) solutions.

Inclusive Voices: Advancing Language Technology for People with Impaired Speech in Local Languages

In April 2025, the CDLI (Centre for Digital Language exclusion) team attended CHI 2025 - the ACM (Association for Computing Machinery) conference on Human Factors in Computing Systems held in Yokohama, Japan. They took part in a workshop on the theme of "Speech AI for All: Promoting Accessibility, Fairness, Inclusivity, and Equity" and made a poster presentation on “Inclusive Voices: Advancing Language Technology for People with Impaired Speech in Local Languages”, which addressed the question of how to promote accessibility, fairness, inclusivity and equity through the use of language technology in local languages for people with impaired speech.

Advancing Speech Technology for All

New report highlights

Kenya innovators join for the latest Centre for Digital Language Inclusion workshops

The Centre for Digital and Language Inclusion (CDLI) has finalised the second phase of its groundbreaking initiative to develop inclusive Automatic Speech Recognition (ASR) systems for individuals with non-standard or impaired speech in African languages. This effort aims to close the digital divide for people with speech impairments and marks a major milestone following a successful pilot in Ghana.

Building Inclusive Speech Recognition for All in Kenya

In today’s digital world, voice technology has become a powerful tool for communication, accessibility, and convenience. From virtual assistants to voice-enabled applications, speaking to devices is now second nature for many.

Enhancing Communication Equity: Evaluation of an Automated Speech Recognition Application in Ghana

In Ghana people who struggle to articulate speech as a result of different conditions experience barriers in interacting with others due to difficulties in being understood. Automatic speech recognition software can be used to help listeners understand people with communication difficulties. However, studies have not looked at the practical feasibility of these technologies beyond the Global North. We present a novel user study examining the introduction of one such technology, Google Project Relate, to Ghana. This freely available mobile application can create personalised speech recognition models in English for non-standard speech to support communication. Our user study spans the training of local speech and language therapists and 20 people with communication difficulties. We utilise the Technology Amplification Theory to contribute insights on the need for technological adaptations, awareness and support to reduce differential gaps of access, capacity and motivation to expand the reach of these technologies rather than exacerbating inequalities.

Google, University of Ghana and GDI Hub to Collaborate

The University of Ghana, Google Research Africa, and UCL’s Global Disability Innovation Hub (GDI Hub) are collaborating on "tɛkyerɛma pa" ("Good Tongue"), an AI-based initiative aimed at improving communication for individuals with non-standard speech patterns. This project focuses on improving AI-powered speech recognition technology for five major Ghanaian languages, marking a significant step in making communication more inclusive for all.

Empower Conference: Automatic Speech Recognition & Voice Cloning

This workshop will demonstrate ElevenLabs technology end to end

Global Disability Summit: Bridging the barrier between non-standard speech and the use of Automatic Speech Recognition

This side event, co-hosted by the Global Disability Innovation Hub and Google at the Global Disability Summit (GDS), explores the intersection of AI and Automatic Speech Recognition (ASR).

Empowering People with Non-Typical Speech in Kenya

GDI Hub’s Centre for Digital Language Inclusion (CDLI) is running an innovation sprint in Kenya

Inclusive Speech Kenya

Accra, Ghana: Using the newly built Akan and Ga ASR models, CDLI and GDI Hub host an inclusive innovation hackathon open to university students across Ghana. From over 150 applicants, 16 teams from across the country progressed to the ideation sprint, mentored by CDLI and University of Ghana and five group finalists presented live to an audience of more than 400 in Accra, including representatives from government, academic institutions and innovators. All teams were provided mentoring to build and demonstrate prototype apps using AI and the language models we had provided. Each team included a person living with speech impairment. Each team utilized local knowledge, skills, experiences and ideas to build solutions for Ghanaians, by Ghanaians. The event, funded by CDLI Hub’s AT2030 programme, demonstrates how local talent can leverage CDLI’s open-source tools for real-world solutions, given the opportunity.

Ghana Pilot Data Collection

Accra, Ghana: CDLI’s first field deployment. Prof. Cathy Holloway and Dr. Richard Cave work with the University of Ghana and Talking Tips Africa to record speech datasets in Akan and Ga languages. Recordings of impaired speech were collected from a diverse group of people living with cerebral palsy, stuttering, trauma, Parkinson’s Disease amongst other conditions, creating one of the first non-standard speech corpora in African languages.

Establishing the Centre

UCL’s GDI Hub launches the Centre for Digital Language Inclusion with support from Google.org, focusing initially on Africa. Partnerships are formulated with the University of Ghana, Talking Tipps Africa and local NGOs to kick-start data collection in Ghana.

Google, University of Ghana and GDI Hub to Collaborate

Google, University of Ghana and GDI Hub will collaborate to Expand AI-Powered Speech Recognition for Non-Standard Speech in Ghanaian Languages