Improving cochlear implant performances by MFCC technique

Cochlear Implant (CI) is a device meant to recover hearing abilities for patients suffering of total bilateral cophosis. In this study we in, to identify phonemes that usually have a low Cl recognition rate. using mel-frequency cepstral coefficients (MFCC) technique. In order to analyse them we had to structure a special signal database: we registered phonemes passed by the Cl testing device. By a technique of accentuating certain frequency bands depending on the recognised phoneme - we intend to improve Cl performances. Clustering is realised by the help of an usual two-layers MLP neural network. In parallel, we extract, using the same steps as in the cochlear implant device technique already implemented, a new set of MFCC coefficients from speech, and compare them. Using fuzzy functions in computing energy on frequency bands results are slightly better [7].