Method for an automated profiling of speech responses in mapping and rehabilitation of speech and system therefor

Abstract

The invention relates to a method for an automated profiling of speech responses in mapping and rehabilitation of speech based on the following steps consisting of performing automatically and fast with minimal human operator effort & intervention, extracting, quantifying, evaluating and assessing the subject's speech and / or its characteristics such as accuracy, quantification of diversions or adherence or conformance to the demanded task, namely errors, semantics, lexical, pragmatics, phonetics, timings, sequential characteristics, of the response in relation to the offered visual, auditory, olfactory, tactile, vibratory, motional template and demanded task performing classification, clustering and modeling of the content and signal characteristics of the sequences of events in the subject responses, producing appropriate utterance's and speaker's profiles augmenting the analysis of the latter step by an appropriate feedback from previous utterance's / speaker's profiles, which are formed by accumulation of previous analyses or beforehand knowledge, maximizing and optimizing the acquired subject or population profile information through an adaptive coordination of the process; by means of a set of proposed operations consisting of the Collection of subject responses, along with a variety of additional data, the Removal of any unwanted signals that may be mixed with the subjectspeech, the Performance of phonetical, phonological, lexical, semantic, and pragmatic NLP along / or after the speech's content recognition, the Performance of intelligent and adaptive coordination of execution flow and selection of the task / paradigm's presentation and interventional parameters, the Building of a system that is structured to be trainable and supervisable, esp. that recurrently accumulates, analyses and makes decisions upon its inputs and outputs, and thus constitutes an intelligent system.