Identification and human condition analysis based on the human voice analysis

Oleksandr Mieshkov, Олександр Новіков, Vsevolod O. Novikov, Leonid S. Fainzilberg, Andrzej Kotyra, Saule S. Smailova, Ainur Kozbekova, Баглан Иманбек

2017

Closed access Metadata (CSL-JSON)

DOI 10.1117/12.2281003

Data confidence 85 high

How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The paper presents a two-stage biotechnical system for human condition analysis that is based on analysis of human voice signal. At the initial stage, the voice signal is pre-processed and its characteristics in time domain are determined. At the first stage, the developed system is capable of identifying the person in the database on the basis of the extracted characteristics. At the second stage, the model of a human voice is built on the basis of the real voice signals after clustering the whole database.