Designing better hearing aids using brain-inspired speech enhance

March 7, 2013

New research is aiming to produce hearing aids which can distinguish better between speech and background noise and benefit the lives of the six million people in the UK with hearing impairments.

Conventional amplify both speech and indiscriminately so they don't make it easy to distinguish meaningful signals, such as speech, from .

To overcome this barrier, researchers from the Universities of Southampton and Cambridge will use knowledge generated from neuronal brainstem recordings to design novel signal processing strategies. By designing this physiological-based algorithm, which mimics how our brain hears sound, the team will be able to identify how individual neurons in the brain stem respond to sound and distinguish meaningful signals from noise.

This 'sparse coding' identification will make it possible for the scientists to reduce levels of noise while increasing speech intelligibility.

Dr Stefan Bleeck, from the Institute of Sound and Vibration Research (ISVR) at the University of Southampton, says: "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 .

"By investigating this coding mechanism in individual neurons, it will allow us 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 resynthesize sound in hearing aids with reduced noise, but with quality intact, to enhance speech intelligibility."

Dr Bleeck has received funding from EPSRC - Healthcare for Engineering to undertake this research with ISVR colleagues Dr Matthew Wright and Thomas Blumensath, and Dr Ian Winter of the University of Cambridge's Department of Physiology.

Dr Bleeck adds: "We expect to see direct applications of our work to be implemented in hearing aids within the next five years. Some of the biggest companies in the world in their field have demonstrated their interest, support and the confidence toward this approach."

Explore further: New research to enhance speech recognition technology

Related Stories

Recommended for you

High-fat diet starves the brain

April 29, 2016

A high-fat diet of three days in mice leads to a reduction in the amount of glucose that reaches the brain. This finding was reported by a Research Group led by Jens Brüning, Director at the Max Planck Institute for Metabolism ...

A vitamin that stops the aging process of organs

April 28, 2016

Nicotinamide riboside (NR) is pretty amazing. It has already been shown in several studies to be effective in boosting metabolism. And now a team of researchers at EPFL's Laboratory of Integrated Systems Physiology (LISP), ...

Lifestyle has a strong impact on intestinal bacteria

April 28, 2016

Everything you eat or drink affects your intestinal bacteria, and is likely to have an impact on your health. That is the finding of a large-scale study led by RUG/UMCG geneticist Cisca Wijmenga into the effect of food and ...

Tiny microscopes reveal hidden role of nervous system cells

April 28, 2016

A microscope about the size of a penny is giving scientists a new window into the everyday activity of cells within the spinal cord. The innovative technology revealed that astrocytes—cells in the nervous system that do ...

0 comments

Please sign in to add a comment. Registration is free, and takes less than a minute. Read more

Click here to reset your password.
Sign in to get notified via email when new comments are made.