Quality Living, Inc., Omaha, NE.
Department of Speech Pathology and Audiology, Miami University, Oxford, OH.
Am J Speech Lang Pathol. 2024 May;33(3):1504-1512. doi: 10.1044/2024_AJSLP-23-00334. Epub 2024 Feb 15.
Text-to-speech (TTS) technology potentially benefits people with aphasia by presenting content through two modalities simultaneously; however, for this to help, eye fixations must synchronize with the auditory rendition of words. Researchers have yet to explore how often and to what extent people with aphasia achieve modality synchronization. This retrospective analysis examined the percent of words people with aphasia see and hear concurrently when reading passages presented via TTS technology. Text-to-speech (TTS) technology potentially benefits people with aphasia by presenting content through two modalities simultaneously; however, for this to help, eye fixations must synchronize with the auditory rendition of words. Researchers have yet to explore how often and to what extent people with aphasia achieve modality synchronization. This retrospective analysis examined the percent of words people with aphasia see and hear concurrently when reading passages presented via TTS technology.
Nine adults with aphasia had their eye movements tracked while processing TTS passages at a preselected default rate of 150 words per minute. Modality synchronization occurred whenever fixation on a written word occurred during the time span beginning 300 ms before auditory presentation and ending at the next word's initiation. Correlations between standardized test scores, unsupported reading rate, and modality synchronization percentages were informative about the association of aphasia and reading impairment severity with achievement of synchronicity.
Three participants demonstrated consistent modality synchronization; average synchronicity ranged from 67% to 76% of passage words. One participant displayed inconsistent synchronization within passages and achieved an average of 58%. The remaining five participants rarely achieved synchronization, with fixations typically lagging substantially behind the auditory presentation. A significant positive correlation occurred between paragraph reading comprehension test scores and modality synchronization percentages.
A default TTS presentation rate does not result in dual modality synchronization for most people with aphasia. This lack of synchronization may contribute to inconsistencies in the benefit people with aphasia experience when provided with TTS support.
文本转语音（TTS）技术通过同时以两种模式呈现内容，为失语症患者带来益处；然而，要实现这一点，眼动必须与单词的听觉呈现同步。研究人员尚未探索失语症患者在多大程度上以及在何种程度上实现了模态同步。本回顾性分析研究了失语症患者在通过 TTS 技术阅读文章时同时看到和听到的单词的百分比。文本转语音（TTS）技术通过同时以两种模式呈现内容，为失语症患者带来益处；然而，要实现这一点，眼动必须与单词的听觉呈现同步。研究人员尚未探索失语症患者在多大程度上以及在何种程度上实现了模态同步。本回顾性分析研究了失语症患者在通过 TTS 技术阅读文章时同时看到和听到的单词的百分比。
9 名成人失语症患者在以预先选定的默认 150 字每分钟的速度呈现 TTS 文章时，其眼动被跟踪。只要在听觉呈现开始前 300 毫秒到下一个单词开始之间的时间段内注视一个书面单词，就会发生模态同步。标准化测试成绩、未支持的阅读速度与模态同步百分比之间的相关性有助于了解失语症和阅读障碍严重程度与同步性实现之间的关联。
3 名参与者表现出一致的模态同步；同步段落单词的平均同步率为 67%至 76%。一名参与者在文章中表现出不一致的同步，平均同步率为 58%。其余五名参与者很少实现同步，他们的注视通常明显滞后于听觉呈现。段落阅读理解测试成绩与模态同步百分比之间存在显著正相关。
大多数失语症患者在默认的 TTS 呈现速度下不会实现双模态同步。这种同步的缺乏可能导致失语症患者在获得 TTS 支持时体验到的益处不一致。
