“I Can’t Talk Now”: Speaking with Voice Output Communication Aid Using Text-to-Speech Synthesis During Multiparty Video Conference

Abstract

COVID-19 has resulted in the rapid popularization of video conferencing. A growing number of users have become obligated to find suitable places for video conferencing, but sometimes they inevitably participate in unsuitable conditions such as noisy or too silent public spaces. However, the video conference experience according to the environment users are in has not been sufficiently discussed. In particular, there is no conducted research on the occasions where video conferencing participants feel unable to speak with their voice due to spatial factors and how to address these situations. In this study, we propose a voice output communication aid (VOCA) for video conferencing which allows users to chat without making a sound. We made a technology probe and conducted a user test. Users who feel unable to speak orally could participate more actively with VOCA. Based on the results, we described the effects and potential of VOCA for video conferencing.