ScholarWorks@숙명여자대학교

초록

Due to the influence of COVID-19, the social environment is changing in the direction of a surge in the frequency of non-face-to-face platform use, but this change rather causes vulnerability in online access for the disabled. In particular, the visually impaired people have difficulty accessing software that emphasizes the importance of visual materials in terms of learning. Accordingly, a speech-based report generation system for the visually impaired has been developed, but the function of inserting visual data into reports is not supported. Therefore, this paper aims to upgrade the existing speech-based report writing system for the visually impaired by implementing image insertion functions such as diagrams as well as general images. When a user searches for the desired image by voice, the system generates a caption for that image, allowing the user to listen to the generated caption by voice and select the desired image and insert it into the report. As a result of the experiment, it was confirmed that visually impaired people can also insert the desired image into the report without much overhead. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

키워드