摘要：This paper presents two early studies aimed at investigating issues concerning the design of multimodal in- teraction - based on voice commands and one-hand mid-air gestures - with mobile technology specifically designed for visually impaired and elderly users. These studies were carried out on a new device allowing enhanced speech recognition (including lip movement analysis) and mid-air gesture interaction on Android operating system (smartphone and tablet PC). We discuss the initial findings and challenges raised by these novel interaction modalities, and in particular the issues regarding the design of feedback and feedforward, the problem of false positives, and the correct orientation and distance of the hand and the device during the interaction. Finally, we present a set of feedback and feedforward solutions designed to overcome the main issues highlighted.
