基于体感控制的语音障碍人群发音训练系统设计及可用性探讨  

Design and usability of voice training system for people with speech impairment based on somatosensory control

作　　者：毛艳梅 Mao Yanmei(Zhejiang University,Hangzhou 310058,China;Zhejiang Business College,Hangzhou 310053,China)

机构地区：[1]浙江大学,浙江杭州310058 [2]浙江商业职业技术学院,浙江杭州310053

出　　处：《无线互联科技》2023年第2期27-31,共5页Wireless Internet Technology

基　　金：浙江省教育厅一般科研项目,项目编号:Y202147638。

摘　　要：基于Kinect的体感控制技术,文章研究了一种语音障碍人群发音训练系统,并通过临床运用测试了系统的可用性。该系统由障碍数据采集、发音康复训练及发音康复评估三大模块构成。每一模块又由文字、图像、声音、视频等多模态内容组建。共有10名语言治疗师、30例语音障碍人群参加了本项研究。研究结果发现基于人工智能深度学习融合技术开发的这套语音康复训练系统可显著提升语音障碍人群的发音质量,具有较好的应用前景。Based on Kinect’s somatosensory control technology,this paper studies a voice training system for people with speech disorders,and tests its usability through clinical application.The system consists of three modules:obstacle data acquisition,pronunciation rehabilitation training and pronunciation rehabilitation evaluation.Each module is composed of text,image,sound,video and other multimodal content.A total of 10 language therapists and 30 people with speech disorders participated in this study.The research results show that the speech rehabilitation training system developed based on AI deep learning fusion technology can significantly improve the voice quality of people with speech disorders,and has a good application prospect.

关 键 词：体感控制 发音训练系统 语音障碍 可用性 

分 类 号：R494[医药卫生—康复医学]