UK voice recognition breakthrough holds promise for speech impairment sufferers

By analysing the physical processes which create the sounds of speech, the team has built a dataset that could underpin the development of speech recognition systems able to read the lips and facial movements of people with speech impairments and provide them with a synthesised voice.

To gather their data, the research group - which includes researcher from the University of Dundee and University College London - asked 20 volunteers to speak a series of vowel sounds, single words and entire sentences while complex scans of their facial movements and recordings of their voices were collected.

The team then used two different radar technologies - impulse radio ultra-wideband (IR-UWB) and frequency modulated continuous wave (FMCW) - to image the movement of the volunteers’ facial skin as they spoke, along with the movements of their tongue and larynx.  Meanwhile, vibrations on the surface of their skin were scanned with a laser speckle detection system, which used a high-speed camera to capture the vibration of emitted laser speckle. A separate Kinect V2camera capable of measuring depth read the deformations of their mouths as they shaped different sounds.