Abstract
This study seeks to investigate the effects of manipulating aspects of a text-to-speech (TTS) voice on the learning and comprehension of a short passage, as well as detection of aspects of the passage such as its organization and key information. Pauses and pitch changes were used to demarcate this type of information. Participants listened to the passages and answered a series of cued and uncued recall questions to measure comprehension and learning, followed by a task to identify header structure. Preliminary results show trends that adding pauses might be beneficial, but more participants are needed to provide conclusive evidence. This study will contribute to the body of research surrounding technology adoption, assistive technology, and how to improve AI voices for the purposes of learning, as well as our understanding of how we process auditory information.
Get full access to this article
View all access options for this article.