Projects

Information accessibility is crucial for all users. There is a gap in information acquisition efficiency between visual readers and screen reader users, particularly in that screen reader users struggle to quickly scan the overall structure of text documents. To bridge this gap, we propose "VoiceCogs", a system that takes text sources composed of multiple items and plays multiple text-to-speech conversions simultaneously to enhance the identifiability of individual sources. We developed and implemented two interlocking techniques to minimize voice interference between concurrent voices.