Suppr超能文献

物联网设备支持自闭症谱系障碍儿童的回声技能发展。

Internet-of-Things Devices in Support of the Development of Echoic Skills among Children with Autism Spectrum Disorder.

机构信息

Virginia Modeling, Analysis & Simulation Center, Old Dominion University, Suffolk, VA 23435, USA.

Mea'Alofa Autism Support Center, Chesapeake, VA 23321, USA.

出版信息

Sensors (Basel). 2021 Jul 5;21(13):4621. doi: 10.3390/s21134621.

Abstract

A significant therapeutic challenge for people with disabilities is the development of verbal and echoic skills. Digital voice assistants (DVAs), such as Amazon's Alexa, provide networked intelligence to billions of Internet-of-Things devices and have the potential to offer opportunities to people, such as those diagnosed with autism spectrum disorder (ASD), to advance these necessary skills. Voice interfaces can enable children with ASD to practice such skills at home; however, it remains unclear whether DVAs can be as proficient as therapists in recognizing utterances by a developing speaker. We developed an Alexa-based skill called ASPECT to measure how well the DVA identified verbalization by autistic children. The participants, nine children diagnosed with ASD, each participated in 30 sessions focused on increasing vocalizations and echoic responses. Children interacted with ASPECT prompted by instructions from an Echo device. ASPECT was trained to recognize utterances and evaluate them as a therapist would-simultaneously, a therapist scored the child's responses. The study identified no significant difference between how ASPECT and the therapists scored participants; this conclusion held even when subsetting participants by a pre-treatment echoic skill assessment score. This indicates considerable potential for providing a continuum of therapeutic opportunities and reinforcement outside of clinical settings.

摘要

对于残疾人士来说,一个重大的治疗挑战是言语和跟读技能的发展。数字语音助手(如亚马逊的 Alexa)为数以亿计的物联网设备提供网络智能,并有潜力为那些被诊断患有自闭症谱系障碍(ASD)的人提供机会,帮助他们提高这些必要的技能。语音界面可以使自闭症儿童在家中练习这些技能;然而,目前还不清楚语音助手是否能像治疗师一样熟练地识别发展中说话者的发音。我们开发了一个名为 ASPECT 的基于 Alexa 的技能,用于衡量语音助手识别自闭症儿童言语的能力。参与者为 9 名被诊断患有 ASD 的儿童,他们每人参加了 30 次会话,重点是增加发声和跟读反应。儿童通过 Echo 设备上的指令与 ASPECT 互动。ASPECT 经过训练可以识别发音,并像治疗师一样对其进行评估——同时,治疗师会对孩子的反应进行评分。研究发现,语音助手和治疗师对参与者的评分没有显著差异;即使对接受治疗前跟读技能评估分数进行子集划分,这一结论仍然成立。这表明,在临床环境之外,提供治疗机会和强化的连续统具有相当大的潜力。

文献AI研究员

20分钟写一篇综述,助力文献阅读效率提升50倍。

立即体验

用中文搜PubMed

大模型驱动的PubMed中文搜索引擎

马上搜索

文档翻译

学术文献翻译模型,支持多种主流文档格式。

立即体验