研究目的
Investigating how gaze and voice modalities could be integrated to provide a better hands-free experience for end-users in web browsing.
研究成果
The multimodal framework combining gaze and voice inputs showed improved performance for hands-free web browsing compared to single modalities. Future work includes enhancing features by integrating low-level semantics of Web pages and conducting thorough evaluations on user adaptation to the multimodal concept.
研究不足
The study had a small sample size of 5 participants for the pilot trial. The accuracy of eye tracking is affected by head position, movement, and ambient lighting. Voice input can be subjective, depending on the accuracy of the technology, privacy, and personal preferences.
1：Experimental Design and Method Selection:
The study involved developing a multimodal browsing framework combining eye gaze and voice inputs for optimized interaction.
2：Sample Selection and Data Sources:
An observational study with 10 participants was conducted to analyze unimodal techniques, followed by a pilot trial with 5 participants to evaluate the multimodal prototype.
3：List of Experimental Equipment and Materials:
SMI RED-n eye tracker with a sampling rate of 60Hz and an inbuilt microphone of a laptop were used.
4：Experimental Procedures and Operational Workflow:
Participants performed browsing operations including search, navigate, and bookmark pages using the multimodal browser, GTW, and HFC.
5：Data Analysis Methods:
The average task completion time was measured for each modality.
独家科研数据包，助您复现前沿成果，加速创新突破
获取完整内容
