Professor Mark Hawley, Director of CATCH features in the current edition of the University of Sheffield’s Discover magazine

Speaking to the publication, Professor Hawley shared the centre’s aims: “Our goal is to help older people, people with disabilities and people with long-term health conditions to help themselves through the use of carefully designed and relevant technology,”

In order to achieve this goal, Professor Hawley takes us through how CATCH works with partners to develop these technologies. “What we specialise in is working with people who are eventually going to use these technologies so they can shape and influence the design of it. That way you get a product which is far more useable by them and is tailored to their needs as opposed to something that the technologist thinks is a great idea.”

Giving the reader a glimpse of the centre’s valuable work, Mark talks about the innovative research team that’s helping people to live independently and be able to self-manage their conditions through user friendly technology.

One current project developing a new assistive technology in the form of an app is explored in the article: “One such development is helping people with neurological disorders who have lost the ability to speak clearly. We are working on a computer program that uses speech recognition technology tailored to an individual, it understands what is being said when they try to speak and interprets this before speaking out a clearer version.” CATCH is currently working to get this technology commercialised. Find out more about the VIVOCA project on our website.

The Centre for Assistive Technology and Connected Healthcare (CATCH) brings healthcare scientists, engineers, psychologists, computer scientists, architects, and social scientists together in a creative hub that is changing lives for the better.

For more information about CATCH or information related to this article, please contact Laura Murray.

To discover other issues of the Discover Magazine please visit this website: Research at Sheffield Website

ARATA Conference 2014, Canberra

Professor Mark Hawley, has been invited to give the key note speech at this years ARATA conference in Canberra from 20-22 August, 2014.

The Australian Rehabilitation & Assistive Technology Association is a national association whose purpose is to serve as a forum for information sharing and liaison between people who are involved with the use, prescription, customisation, supply and ongoing support of assistive technology.

Mark will give a talk entitled 'From Assistive Technology to Assisted Living: the changing face of technology support for independence, health and care'

Mark will also be giving a presentation to the Voice Input Voice Output Communication Aid VIVOCA for people with disordered speech.

For more information on this conference, please click here.
 

For more information on VIVOCA, please click here.

VIVOCA participant makes a difference!

Peter (VIVOCA participant) has been involved in one of our research projects, VIVOCA (Voice Input Voice Output Communication Aid), for several months and has offered many insightful and practical suggestions which we’ve incorporated to improve our designs. From our point of view he has been a great candidate – full of ideas and never one to hold back on suggestions or opinions.

The article below was published in the local MNDa magazine describes Peter’s perspective of being an active research participant. The article has now been accepted for the national MND publication “Thumb Print”.

Written by Andrea Kirton

VIVOCA: Voice Input Voice Output Communication Aid - Interview with Professor Mark Hawley

Professor Mark Hawley

Professor Mark Hawley; director of the RAT Group and CATCH and VIVOCA lead researcher spoke about speech impairment, how VIVOCA  can help people with impaired speech and his plans for the future. Click here to view article.

Mark Hawley to give keynote lecture at Workshop on Speech and Language Processing for Assistive Technologies (SLPAT)

Mark Hawley has been invited to give the keynote lecture at this year’s Workshop on Speechand Language Processing for Assistive Technologies (SLPAT) in Grenoble on 21-22 August. His talk will be entitled ‘Speech and Language Processing for Assistive Technologies in practice: lessons from translational research'.

The talk will distil experience and results from several projects, over more than a decade, which have researched and developed the application of speech recognition as an input modality for assistive technology (AT). Current interfaces to AT for people with severe physical disabilities, such as switch-scanning, can be prohibitively slow and tiring to use. Many people with severe physical disabilities also have some speech, though many also have poor control of speech articulators, leading to dysarthria. Nonetheless, recognition of dysarthric speech can give people more control options than using body movement alone. Speech can therefore be an attractive option for AT input.

Techniques that have been developed for optimising the recognition of dysarthric speech will be described, resulting in recognition rates of greater than 80% for people with even the most severe dysarthria. Speech recognition has been applied as a means of controlling the home (via an environmental control system) and, probably for the first time, as a means of controlling a communication aid. The development of the Voice Input Voice Output Communication Aid (VIVOCA) will be described and some early results of its evaluation presented (see previous blog post for open access to the project's most recent publication).

The talk will discuss some of the lessons learnt from these projects, such as:

·       The need to work in interdisciplinary teams including speech technologists, speech and language therapists, health researchers and assistive technologists

·       The value of user-centred design, involving users in defining their wants and needs and then working with them, in an iterative manner, to refine the AT such that it becomes usable and acceptable

·       The gap that exists between the results that can be achieved in the lab and those achievable in people’s homes under real usage conditions –something that is not often covered in research papers

·       The practical approaches that can be applied to optimising recognition for individuals. It is often possible to make significant improvements in recognition rates by altering the configuration of the AT set-up.

The talk will conclude by describing some of the future potential applications of speech technology that are being developed, or considered, for people with disabilities as well as for frail older people and people with long-term conditions.

[Written by Mark Hawley]

VIVOCA paper is 2nd most popular download from IEEE Transactions on Neural Systems and Rehabilitation Engineering

The VIVOCA (Voice Input Voice Output Communication Aid) paper reported in the RAT blog at the end of February is proving to be a popular read. "A Voice-Input Voice-Output Communication Aid for People with Severe Speech Impairment" has been downloaded nearly 400 times since August 2012 and has become the 2nd most popular download from IEEE Transactions on Neural Systems and Rehabilitation Engineering.

The paper explains the development of the prototype system that uses speech recognition to help people with severe speech impairment control their VOCA. Work is still continuing on this topic with the VIVOCA2 project, funded by the National Institute for Health Research (NIHR). There is more information on this project here.

The paper is open access, available for download free of charge through the IEEE Xplore site.

Reference:
Hawley, M.S.; Cunningham, S.P.; Green, P.D.; Enderby, P.; Palmer, R.; Sehgal, S.; O'Neill, P., "A Voice-Input Voice-Output Communication Aid for People With Severe Speech Impairment," Neural Systems and Rehabilitation Engineering, IEEE Transactions on, vol.21, no.1, pp.23-31, Jan. 2013
doi: 10.1109/TNSRE.2012.2209678

Developing a voice input voice output communication aid - new paper published (open access)

Developing a voice input voice output communication aid

Some people with severe speech difficulties rely on a voice output communication aid or VOCA to help them communicate with others. Perhaps the most famous VOCA user is Professor Stephen Hawking.

Many others also rely on these devices in their everyday lives. For some however these devices might not be ideal. People who have some speech prefer to use their own voice to communicate. They will often only use a VOCA as a last resort if they are having difficult making themselves understood.

Unfortunately it can also take time to compose a message on a VOCA, often requiring the user to look at the screen, and break eye contact with their conversation partner.

We have been looking a novel way of using speech recognition to help VOCA users to compose their messages. We hope that using speech might be faster, and more intuitive way of using a VOCA.

In a paper recently published in the IEEE Transactions on Neural Systems and Rehabilitation Engineering we explain the development of a prototype system that using speech recognition to help users control their VOCA .

We are now continuing this work in the VIVOCA2 project which is funded by the National Institute for Health Research (NIHR) - you can find out more about this project here.  

[written by Stuart Cunningham]