A researcher giving instructions to a man wearing a headset who is about to bank his voice

Speak:Unique voicebank research

Speak:Unique voicebank research

Creating personalised voices for use in communications aids, simply and efficiently.

For millions of years, mankind lived just like the animals. Then something happened which unleashed the power of our imagination. We learned to talk and we learned to listen. Speech has allowed the communication of ideas, enabling human beings to work together to build the impossible. Mankind’s greatest achievements have come about by talking, and its greatest failures by not talking. It doesn’t have to be like this. Our greatest hopes could become reality in the future. With the technology at our disposal, the possibilities are unbounded. All we need to do is make sure we keep talking.

Professor Stephen Hawking (1942- 2018)

Sadly, MND can sometimes leave people unable to speak. This leads to isolation, difficulty communicating, and loss of control, dignity and personal identity.

Some people in this situation choose to use a communication aid or app that can convert text, entered on a keyboard or by eye movements, into a computerised voice. These devices are valuable, but the pre-installed generic or “off the shelf” voices provide a very limited solution.

Speak:Unique, our Voicebank Research Project, aims to help people with MND sound like themselves again, by providing ‘their own’ voice for use in a communication aid.

The technology

In collaboration with the Centre for Speech Technology Research at the University of Edinburgh, we have developed technology that can create a synthetic version of an individual’s voice. These synthetic voices can then be integrated into the user’s communication aid, to allow them to communicate with a voice that is identifiably theirs.

We aim to record the individual reading aloud 400 sentences, but we can record as little as 100 sentences, which takes around 15 minutes. We then match the individual’s voice to a corresponding accent template and use this to create the synthetic voice. Our accent templates are a collection of around 25 different voice “donors”, grouped together by age, gender and regional accent (e.g. Glaswegian, Borders, or Orkney).

The accent templates help us to boost the amount of recorded speech available, allowing us to record individuals for a short amount of time. The accent templates also allow us “repair” voices. If at the time of recording the individual’s voice has become impaired (e.g. through slurring), we can use the accent template to repair this damage. This repair process can be further enhanced by mixing in the voice of a nominated voice donor (e.g. a sibling or childhood friend) who sounds similar.

To create our accent templates we record ‘donor’ voices from volunteers. we currently have enough recorded voices  for nearly all of Scotland but we are still looking for a few more Scottish accents. We’re also collecting English, Irish and Welsh accents now too. Find out if we need your accent by visiting the Speak:Unique website

Our vision

We are working hard to offer this technology more widely. Ultimately, we want everyone who has a condition that means they are unable to speak, or that might cause them to lose this ability, to be able to communicate in a voice that is theirs.

What we can offer now

Speak:Unique is still a research project.

Regrettably we can’t yet provide bespoke voices to individuals.

We are improving the technology and user interfaces, and testing it out on a small number of people with MND.

We’re also still building up our bank of donor healthy voices. Our Scottish accents are nearly complete, but there’s still a few more we need. We’re collecting English, Irish and Welsh accents now too. Find out if we need your accent by visiting the Speak:Unique website.

Speak:Unique website