Typetalker: A Speech Synthesis-Based Multi-Modal Commenting System

Speech commenting systems have been shown to facilitate asynchronous online communication from educational discussion to writing feedback. However, the production of speech comments introduces several challenges to users, including overcoming self-consciousness and time consuming editing. In this paper, we introduce TypeTalker, a speech commenting interface that presents speech as a synthesized generic voice to reduce speaker self-consciousness, while retaining the expressivity of the original speech with natural breaks and co-expressive gestures. TypeTalker streamlines speech editing through a simple textbox that respects temporal alignment across edits. A comparative evaluation shows that TypeTalker reduces speech anxiety during live-recording, and offers easier and more effective speech editing facilities than the previous state-of-the-art interface technique. A follow-up study on recipient perceptions of the produced comments suggests that while TypeTalker's generic voice may be traded-off with a loss of personal touch, it can also enhance the clarity of speech by refining the original speech's speed and accent.