Search

In this work, a bioinspired or neuromorphic model to replicate the vowel recognition process for an auditory system is presented. A bioinspired peripheral and central auditory system model is implemented and a neuromorphic higher auditory system model based on artificial neuronal nets for vowel recognition is proposed. For their verification, ten Hispanic Spanish language-speaking adults (five males and five females) were used. With the proposed bioinspired model based on artificial neuronal nets it is possible to recognize with high levels of accuracy and sensibility the vowels phonemes of speech signals and the assessment of cochlear implant stimulation strategies in terms of vowel recognition.

Cochlear implants are devices which are surgically inserted into the internal ear, partially restoring hearing to people with profound deafness. Alternatives to improve levels of auditory perception are to increase the number of channels or frequency bands, that would need to increase the number of electrodes or electrode pairs per channel. Monopolar Virtual Channel (MPVC) stimulation mode increases the number of channels without increasing the number of electrodes using current steering. With this stimulation mode what still happens is interaction between the virtual channels, so some people who have these implants have not reported a striking improvement. In the present work, parameters of this electrical stimulation mode are modeled and evaluated. The results suggested that the maximal stimulation current can be determined so that no electrical interaction will occur between adjacent channels. If the stimulation current is higher than the calculated value, electrical interactions will occur between adjacent channels.