Quadtree based mouse trajectory analysis for efficacy evaluation of Voice-enabled CAD

Abstract

Voice-enabled applications have caught considerable research interest in recent years. It is generally believed that voice based interactions can improve the working efficiencies and the overall productivities. Quantitative evaluations on the performance boost by using such Human-Computer interactions (HCI) are therefore necessary to justify the claimed efficacies and the usefulness of the HCI system. In this paper, a quadtree based approach is proposed to analyze the mouse movement distributions in the proposed Voice-enabled Computer-Aided Design (VeCAD) system. The mouse tracker keeps a record of all the mouse movement during the solid modeling process, and a quadtree based approach is applied to analyze the mouse trajectory distributions in both the traditional CAD and the VeCAD system. Our experiments show that the mouse movement is significantly reduced when voice is used to activate CAD modeling commands.

Multimodal Natural Human–Computer Interfaces for Computer-Aided Design: A Review Paper

“…With the rapid development of speech synthesis and recognition technologies in recent years, speech-based HCIs have been extensively employed in a variety of household, automobile, office, and driving applications [48,97]. In particular, voice-enabled intelligent personal assistants (IPAs), such as Amazon's Alexa, Apple's Siri, Google Assistant, and Microsoft Cortana, are widely available on a number of automatic devices [97].…”

“…These CAD commands could be realized naturally and directly through a speech-based interface. Therefore, some studies tried converting the names of menus and icons into voice-controlled commands [48][49][50][51][52][53]. Most of these studies were aimed at using fixed expressions to perform modeling operations.…”