Fundamental frequency evaluation subsystem for natural speech rehabilitation software calculation module for cancer patients after larynx resection

Abstract

This article describes the speech signal fundamental frequency evaluation algorithm in view of speech formation and speech perception features connected with human anatomy and physiology, using mathematical apparatus of singular spectrum analysis for speech signal processing, for further implementation of the speech signal fundamental frequency evaluation subsystem, designed for speech rehabilitation software calculation module for cancer patients after larynx resection, used in patients rehabilitation trainings process after their full or partial loss of sonorous speech arising from laryngectomy. The researcher's results of functional testing are described. Also the results of initial testing on a group of healthy speakers are presented.