Predicting the Impact of Hearing Aid Processing on Speech Intelligibility Seminar
- Time:
- 12:00 - 13:00
- Date:
- 27 November 2019
- Venue:
- B19 room 3011
For more information regarding this seminar, please telephone Mrs Satwant Virdee on Ext 22277 or email s.virdee@soton.ac.uk .
Event details
HABC seminar
About 2 million people in the UK use hearing aids, but it is estimated that a further 4.7 million could benefit from hearing aid use. Although the National Health Service devotes roughly an annual £450 million to addressing hearing loss, the additional indirect cost to the UK government due to associated health, social and economic effects of untreated hearing loss is estimated to be at least £30 billion every year. Hearing aid users rate performance in noise, particularly for speech listening, as the most valued yet least satisfactory attribute of their hearing aids. Development of automated metrics to predict speech intelligibility (rather than performing speech-in-noise tests) could speed up the assessment procedure for speech processing in hearing aids. This in turn could reduce the time and cost to both the NHS and to hearing aid manufacturers involved in developing and assessing hearing aids with regards to speech listening.
The study detailed in this presentation compares intelligibility of IEEE sentences in collocated speech-shaped noise, recorded through a low-cost amplifier and three current-issue NHS hearing aids with single-channel noise reduction settings switched on and off. Results from twenty-one normal hearing listeners indicates that single-channel noise reduction algorithms can significantly improve intelligibility of noisy speech, but no differences can be seen between different hearing aid models currently available on the NHS. The low-cost, off-the shelf hearing amplifier performed significantly worse than the NHS prescribed devices. Three automated speech intelligibility measures were also applied to the recordings. Discussion of the application, benefits and limitations of these automated speech intelligibility metrics will be given.
Speaker information
Robyn Hunt , Postgraduate Researcher. ISVR, University of Southampton