Third International Conference on Spoken Language Processing (ICSLP 94)
In this paper, a multimodal drawing tool S-tgif is developed to verify the effectiveness of speech in human-machine interface. The system is designed in consideration of the basic principles and organization principles of interface that are required for comfortable input systems. Desired organization of interface using speech, mouse and key-board is discussed from the viewpoints of less physical movement, easiness to learn, and transparency of the system. As the results, the multimodal drawing tool with speech recognition reduces average operation time to 71%, the number of command operation to 77%, and movement of mouse pointer to 53% in evaluation with inexperienced users.
Bibliographic reference. Nishirnoto, Takuya / Shida, Nobutoshi / Kobayashi, Tetsunori / Shirai, Katsuhiko (1994): "Multimodal drawing tool using speech, mouse and key-board", In ICSLP-1994, 1287-1290.