A Training System for Speech Disordered Children Based on the Intel RealSense Technology

DOI

10.2991/caai-17.2017.113How to use a DOI?

Keywords

speech rehabilitation; Intel realsense; human-machine interaction; speech recognition

Abstract

A training system for speech disordered children is presented in this research. The core technology includes face tracking and speech recognition, which are supplied by Intel RealSense SDK and its relative hardware, such as 3D camera F200. The system consists of the pronouncing learning module and the speech disorder training module. The former can help children patient with almost no speech ability learn the pronouncing motion and method in Mandarin initials and finals with real-time 3D image playback. The training module which is based on the cartoon games can intervene patients' abnormal voice onset, speech volume, speech tone and vowel confusion. With the help of the speech recognition function from Intel RealSense, it can make an immersed environment which is benefit for training.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Boyu Si
AU  - Zhaoming Huang
AU  - Baodan Bai
PY  - 2017/06
DA  - 2017/06
TI  - A Training System for Speech Disordered Children Based on the Intel RealSense Technology
BT  - Proceedings of the 2017 2nd International Conference on Control, Automation and Artificial Intelligence (CAAI 2017)
PB  - Atlantis Press
SP  - 504
EP  - 507
SN  - 1951-6851
UR  - https://doi.org/10.2991/caai-17.2017.113
DO  - 10.2991/caai-17.2017.113
ID  - Si2017/06
ER  -