Evaluation of contrast enhancement algorithms for hearing aid and cochlear implant processing
Summary:
Users of hearing aids (HA) and cochlear implants (CI) experience particular difficulties when listening to speech in noise. The impaired auditory system and hearing instrument effectively impose a bottleneck that restricts information transmission to the auditory system. The project will explore a novel approach by the use of redundancy reduction algorithms for different patient groups (e.g. HA users, CI users) and optimisation for individuals. The project will also develop real-time implementation of the algorithms and carry out subsequent field trials.
References:
Hyvarinen, A. and E. Oja, A fast fixed-point algorithm for independent component analysis. Neural Computation, 1997. 9(7): p. 1483-1492.
Smaragdis, P., Redundancy reduction for computational audition, a unifying approach. 2001, Massachusetts Institutes of Technology
