Detection Childhood of Apraxia of Speech From the Video Data Using PoseNet

Zhibek Daribay, Magzhan Kairanbay, Zhanali Daribayev

2022

Closed access Metadata (CSL-JSON)
DOI 10.1109/sist54437.2022.9945794
Data confidence 70 medium
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

Childhood of Apraxia of Speech (CAS) is a type of disorder that affects the speech of the children. Children who have a CAS found it difficult to control and coordinate the brain's neutrons in order to create sounds for the phrases. Therefore, while talking they behave themselves in abnormal way. This research work proposes the Computer Vision based solution in order to diagnose the patients agains CAS based on video content. We will be using the PoseNet Convolutional Neural Network (CNN) in order to track the pose of the child and fix abnormal behaviour while giving the interview. As a result we will be able to automatically identify whether the child has CAS or not.