Gender differences in multi-modal interface system for 3D object modelling

With the advancement in technology, the multi-modal interface system (MMIS) is now becoming a vital part of almost every intelligent system. The multi-modal interface system uses humanlike input to convey information to a computing device instead of typical mouse/keyboard inputs. However, the acceptance of an MMIS by individuals depends upon various factors related to both the users and the system. This study focuses on investigating the gender-related factors affecting the performance of an MMIS in 3D object modelling applications. The multi-modal inputs used in this study are speech and gestures. The participants model a 3D object in AutoCAD using both traditional keyboard/mouse inputs and multimodal speech/gesture inputs. The data has been collected through questionnaires and audio/video log files. The initial finding confirms that there exists a gender-based difference. The results indicate female participants are more comfortable using speech and gesture inputs compared to male participants. The findings also suggest that the performance of the MMIS is not just task-specific but also gender-specific.