It is well known that normal hearing listeners can better understand speech in noise when listening with two ears rather
than with only one. Differences between the signals at the two ears allow the speech and noise to be separated based on
their spatial locations resulting in improved intelligibility. It
is the goal of this project to exploit these binaural advantages by developing speech enhancement algorithms that jointly
enhance the speech received by the two ears. [ more information ]
The project aims:
- To extend existing single-channel intelligibility metrics to encompass binaural listening with both normal-hearing and
- To develop methods for the blind adaptive estimation of acoustic parameters that characterise the listening environment
- To develop methods to estimate binaural time-frequency masks that improve the intelligibility of speech-in-noise for
hearing-impaired listeners without unacceptably degrading quality.
- To develop methods that automatically modify the enhancement regime of a hearing aid dynamically in response to the
listening environment and context.