News

Oscar

/

Oscar's Story "We should not be left behind."

Link Copied!

Ghana

04 Jun 26

For Oscar, a barber in Accra born with a cleft palate, the stakes are high. He describes the isolation of having to write down thoughts because of the difficulty of being understood with his condition.

"We need to associate with all human beings, how they talk, how they react, so that the machines too will understand them."

‍

As the world races toward an AI-driven future, millions with slurred or difficult-to-understand speech are being "left out of the algorithm". The Centre for Digital Language Inclusion (CDLI) led by University College London’s (UCL) Global Disability Innovation Hub (GDI Hub) are harnessing the power of AI to develop pioneering automatic speech recognition (ASR) solutions for impaired speech.

With the aim of making speech recognition software accessible to everyone, the centre is collecting and sharing impaired speech data while training AI models to recognise impaired speech.

Award winning Witness Studios, a creative company telling real human stories with sensitivity and cinematic craft, joined the CDLI in Ghana to capture intimate and poetic portraits of people who have the most to gain from inclusive research, yet currently find their voices categorised as "noise" by standard technology.

Launching on World Day for Assistive Technology, these films focus on the potential of digital assistive technologies - and the importance of ensuring no-one is left out of the algorithm during this critical stage of AI and ASR innovation.

Ghana

04 Jun 26

Related

When we speak films

World Day for Assistive Technology is an annual celebration on the 4th June, that champions the importance of assistive technology (AT) to increase access and raise awareness, especially in low- and middle-income countries.

When we speak film

Award-winning Witness Studios, a creative company telling real human stories with sensitivity and cinematic craft, joined the CDLI in Ghana to capture intimate and poetic portraits of people who have the most to gain from inclusive research, yet currently find their voices categorised as "noise" by standard technology.

Radia

Radia's Story: "people around you cannot get you."

© 2026 CDLI. All rights reserved. Site by

Accessibility

Accessibility, A11y

The design of technologies, services, and environments so they can be used by people with diverse abilities, including people with disabilities.

Assistive Technology

Assistive Technology

Tools or systems that help people with disabilities perform tasks more easily. Inclusive speech recognition can function as assistive technology for communication.

Automatic Speech Recognition (ASR)

Automatic Speech Recognition (ASR), Automatic Speech Recognition, ASR

Technology that converts spoken language into written text. ASR enables devices and software to "understand" human speech and is used in tools such as voice assistants, transcription services, and accessibility technologies.

Community-Centred Design

Community-Centred Design, Community Centred Design

An approach that actively involves people who will use the technology in its design, development, and testing, ensuring solutions reflect real needs and lived experiences.

Data Annotation

Data Annotation

The process of labelling speech recordings with accurate text or metadata. Annotation helps machines learn how spoken words relate to written language.

Digital Language Inclusion

Digital Language Inclusion

The practice of ensuring that digital technologies recognise, understand, and support all ways people speak, including diverse languages, accents, and speech patterns.

Ethical Data Collection

Ethical Data Collection

The practice of collecting data with informed consent, transparency, privacy protection, and respect for participants' rights and dignity.

Inclusive AI

Inclusive AI

Artificial Intelligence systems designed to work fairly and effectively for people of different abilities, languages, and backgrounds, without excluding or disadvantaging certain groups.

Machine Learning

Machine Learning

A branch of AI that allows computer systems to learn patterns from data and improve their performance over time without being explicitly programmed for every task.

Non-Standard Speech

Non-Standard Speech

Speech that differs from what most speech recognition systems are trained on. This may include speech affected by disability, neurological conditions, injury, accent variation, or local language patterns.

Open-Source

Open-Source, opensource, open source

Software, data, or models that are freely available for anyone to use, study, modify, and share. CDLI promotes open-source approaches to accelerate inclusive innovation.

Speech Dataset

Speech Dataset

A structured collection of recorded speech samples and corresponding text. These datasets are used to train and improve speech recognition models.

Speech Impairment

Speech Impairment

A condition that affects a person's ability to produce clear or typical speech. This can be temporary or lifelong and may result from disability, illness, injury, or neurological differences.

Speech Model

Speech Model

A trained AI system that processes and recognises spoken language. Speech models improve as they are exposed to more diverse and representative speech data.

Under-Resourced Languages

Under-Resourced Languages, Under Resourced Languages

Languages that lack sufficient digital data, tools, or technological support. Many African languages fall into this category, making them poorly supported by mainstream speech technologies.