Next gen hearing aid promises greater clarity
UK researchers are working to create hearing aids that can better distinguish between speech and background noise.
The team, from the Universities of Southampton and Cambridge, is using knowledge generated from neuronal brainstem recordings to design novel signal processing strategies.
By designing this physiological-based algorithm, which mimics how the brain hears sound, the aim is to identify how individual neurons in the brain stem respond to sound and distinguish meaningful signals from noise.
The researchers believe this 'sparse coding' identification will make it possible to reduce levels of noise while increasing speech intelligibility.
Dr Stefan Bleeck, from the Institute of Sound and Vibration Research at the University of Southampton, said: "Our central hypothesis is that the brain uses sparse coding when distinguishing meaningful signals from noise and it uses a dynamic dictionary for sound representation.
"Neurons adapt their response because they have a limited dynamic rate which they constantly optimise in response to noise in order to reduce redundancy and to maximise the information flow.
By investigating this coding mechanism in individual neurons, Dr Bleeck believes the team will be able to develop novel signal processing algorithms to select the parts that code speech and the ones that code unwanted noise.
"We will then be able to resynthesise sound in hearing aids with reduced noise, but with quality intact, to enhance speech intelligibility," he added.
The researchers have received £600,000 funding from the EPSRC for the hearing aid, as part of a £12.2million investment in 15 creative engineering research projects.
"We expect to see direct applications of our work to be implemented in hearing aids within the next five years," Bleeck concluded. "Some of the biggest companies in the world in their field have demonstrated their interest, support and the confidence toward this approach."
