The Centre for Digital Language Inclusion (CDLI)

Advancing non-standard speech in Automatic Speech Recognition

Get Involved

Partners

A union jack with the text "UK Aid, from the British people" underneath it.

Stylised question mark and exclamation mark merged together alongside the words Keio Media Design

Shield accompanied by the text University of Ghana

About

Automatic Speech Recognition (ASR) is transforming the ability of people with non-standard speech to communicate. The prevalence of mobile devices, alongside free to access apps are making ASR accessible, convenient and less stigmatising for people with slurred or difficult-to-understand speech.

The Centre for Digital Language Inclusion (CDLI) is pioneering inclusive ASR solutions for people with non-standard speech around the world.

Research

AI-powered communication tools have the potential to transform lives. Yet, many in Africa with non-standard speech lack access to this technology or traditional speech therapy.

The Centre for Digital Language Inclusion will advance digital language inclusion by:

Ensuring all languages and types of speech are supported by technology.
Developing inclusive solutions for people with communication difficulty.
Ensuring people know and can use the technology available to them.

Impact

Harnessing the power of Artificial Intelligence (AI) these communication solutions have the potential to change lives.

Currently this technology is not available to those who would most benefit - non-English speaking populations in African countries, who often have the least access to traditional assistive technology and speech and language therapy.

First Steps

Collecting datasets of non-standard speech for 10 African languages, the CDLI will build ASR models, develop AI-driven inclusive communication technologies and train others in the use of this innovative technology.

A proven method of communication once language models are created, this is the first time non-standard speech will have been collected for ASR in native African languages, enabling the millions most in need of inclusive communication technology to access these new solutions.

News & Events

View All ›

Image of a promotional poster for the GDS side event

Highlight

Global Disability Summit: Side Event Al for development - bridging the barrier between non-standard speech and the use of Automatic Speech Recognition

Join us at the Global Disability Summit for a special event on AI and speech recognition, co-hosted by Google and the Global Disability Innovation Hub. Discover how AI is transforming communication for people with non-standard speech through inclusive, locally driven innovation. Featuring insights from the AT2030 Programme and the new Centre for Digital Language Inclusion.

Centre for Digital Language Inclusion in Ghana

GDI Hub’s Richard Cave and Catherine Holloway are in Ghana advancing the Centre for Digital Language Inclusion (CDLI), launched with UCL, University of Ghana, and Talking Tipps Africa. CDLI is collecting non-standard speech data in African languages to build inclusive, open-source AI speech recognition tools, ensuring accessibility for disabled people with communication barriers.

Changing lives through AI - a new Centre for Digital Language Inclusion will bridge the barrier between non-standard speech and the use of Automatic Speech Recognition for disabled people worldwide

UCL’s GDI Hub has launched the Centre for Digital Language Inclusion to develop AI-powered speech recognition for people with non-standard speech, focusing on African languages. In partnership with global institutions and with support from Google.org, the Centre will collect open-source datasets, train communities, and create inclusive communication technologies for underserved populations.