Scientists given £6.2m for talking computers
Researchers will use sophisticated computing techniques to create a combined system that can not only understand the spoken word well but can also synthesise voices that sound natural.
The technology will be equipped with artificial intelligence to enable it to become familiar with a user’s voice.
Advertisement
Hide AdAdvertisement
Hide AdScientists say the technology could have many benefits, including improved voice-activated computers.
It may also help to develop web search engines for audio clips, as well as potentially creating voice-controlled devices for the home, which could help older people stay independent.
Researchers from the Universities of Edinburgh, Cambridge and Sheffield aim to develop the systems over the next five years.
Professor Steve Renals, of the University of Edinburgh’s School of Informatics, is leading the project.
Advertisement
Hide AdAdvertisement
Hide AdHe said: “We are working to develop technologies that can recognise and generate natural-sounding speech.
“This could open the door to computer speech technology becoming commonplace throughout our lives – at home, at work, and in our leisure time.”
It is hoped that technology which responds to speech could soon be able to recognise an individual’s voice and become familiar with their vocabulary, accent and vocal expressions.
It could also be able to follow the flow of a conversation and to gloss over changes in background noise.
Advertisement
Hide AdAdvertisement
Hide AdThe project is funded by the Engineering and Physical Sciences Research Council.
Dr Thomas Hain, of the University of Sheffield’s Department of Computer Science, added: “Speech technology is clearly on its way into the mainstream, but the key to its success is human-like performance.
“We are working on the foundations of technology that will bring speech to new users and exciting new applications, from clinical assistive technology to robotics, from schools to board rooms.”
Professor Phil Woodland of Cambridge University’s Engineering Department added that the focus of natural speech technology is to develop a system that can achieve human-like performance and behaviour.
He said the group are particularly interested in improving the ability of the technology to learn about and adapt to particular users and contexts.