Speech Recognition as a Practice Tool for Dysarthria.
Speech Recognition as a Practice Tool for Dysarthria.
复制标题
语音识别作为构音障碍的练习工具。
DOI：
10.1055/s-0037-1602841
复制
发表时间：
2017
影响因子：
1
通讯作者：
Fager,SusanKoch
中科院分区：
文献类型：
--
作者：
Fager,SusanKoch
构音障碍的言语恢复需要大量的时间和练习。语音识别（SR）技术可以支持构音障碍患者的长期练习和语音恢复工作。然而，SR技术的发展一直集中在典型的（神经完整的）扬声器，以支持写作。本文介绍了SR技术的历史和发展，它是如何被用于个人构音障碍，并包括一个案例研究说明使用一种新的SR技术作为语音练习工具。病例研究参与者包括两个不同的发病和构音障碍，由于创伤性脑损伤的个人。结果表明，双方都能够在语音练习过程中的声学/感知的变化，和一个参与者表现出泛化的变化，习惯性的讲话。讨论了当前SR技术作为语音练习工具的局限性和未来发展方向。
Recovery of speech in dysarthria requires an extensive amount of time and practice. Speech recognition (SR) technology may support long-term practice and speech recovery efforts for individuals with dysarthria. However, SR technology development has been focused on typical (neurologically intact) speakers to support writing. This article describes the history and development of SR technology, how it has been used by individuals with dysarthria, and includes a case study illustration of the use of a novel SR technology as a speech practice tool. Case study participants included two individuals with differing onsets and dysarthria due to traumatic brain injury. Results indicated that both were able to make acoustic/perceptual changes during speech practice sessions, and one participant demonstrated generalization of changes to habitual speech. Limitations and future directions of current SR technology as a speech practice tool are discussed.