Selective Phoneme Spotting for Realization of an /s, z, C, t/ Transposer

Abstract

Hearing impaired people with severe sensory deficit urgently need a perception-based replacement for inaudible fricational features of /s, z, C, t/ (beyond NR and speech enhancement) - to restore high-level breakdown of speech connectedness. Today, shortcomings of past designs can be overcome by digital processing, introducing naturalness and selectivity in the synthetsized stimuli. The ears’ lost selectivity may partially be substituted by the functionality of a dedicated phoneme (class) spotter - based on statistical feature recognition. Subserving transposition, simplified spotting procedures yield sufficient quality of classification, which provides a valid basis for implementation on wearable low-power DSPs of today.