Department is part of a new EU consortium researching solutions for speech problems

The Department of Computer Science is part of a European-wide project which aims to transform the well-being of people with debilitating speech problems.

The Training Network on Automatic Processing of PAthological Speech (TAPAS) is a Horizon 2020 Marie Skłodowska-Curie Actions Initial Training Network European Training Network (MSCA-ITN-ETN).

There are an increasing number of people with debilitating speech pathologies, for example, due to a stroke or Parkinson's disease. These groups face communication problems that can lead to social exclusion. They are now being further marginalised by a new wave of speech technology that is increasingly woven into everyday life but which is not robust to atypical speech - services like Amazon Echo or iPhone’s personal assistant, Siri. TAPAS is proposing a programme of pathological speech research, that aims to transform the well-being of these people.

The TAPAS research will focus on three key issues:

  1. Detection: developing speech processing techniques for the early detection of conditions such as Alzheimer’s disease and Parkinson’s disease, which have an impact on speech production. The outcomes will be inexpensive and non-invasive diagnostic tools that provide early warning of of the onset of such progressive conditions.
  2. Therapy: We will use newly-emerging speech processing techniques to produce automated speech therapy tools. These tools will make therapy more accessible and more individually targeted. Better therapy can increase the chances of recovering intelligible speech after traumatic events such a stroke or oral surgery.
  3. Assisted Living: We will re-design current speech technology so that it works well for people with speech impairments and also helps in making informed clinical choices. People with speech impairments often have other co-occurring conditions making them reliant on carers. Speech-driven tools for assisted-living are a way to allow such people to live more independently.Two of the fifteen research projects will be hosted at The University of Sheffield by Dr Heidi Christensen from our Department of Computer Science, who said: “The first of our projects aims to develop speech technology that can detect, as early as possible, a decline in cognitive ability which might lead to dementia.

Two of the fifteen research projects will be hosted at The University of Sheffield by Dr Heidi Christensen from our Department of Computer Science, who said: “The first of our projects aims to develop speech technology that can detect, as early as possible, a decline in cognitive ability which might lead to dementia.

“In the second project, the student will explore methods for those with speech impairments towards enabling them to use larger-vocabulary, phrase based speech recognition.

“We are looking forward to getting these projects underway and helping to transform the lives of people with serious speech problems.”

TAPAS is adopting an interdisciplinary and multi sectoral approach. The consortium of EU partners includes clinical practitioners, academic researchers and industry, with expertise covering speech engineering, linguistics and clinical science.

This network will train a new generation of 15 researchers, providing them with the necessary skills and resources based on the research themes outlined above.

Any Early Stage Researchers interested in working on these projects are invited to apply using this form: https://www.tapas-etn-eu.org/positions/recruitment