An experimental study of future “natural” multimodal human-computer interaction

Mignot, Christophe; Valot, Claude; Carbonell, Noëlle

doi:10.1145/259964.260075

Cited by 28 publications

(11 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Mignot et al's study of a multimodal (speech + gesture) system for furniture layout [11] found that users preferred speech for more abstract commands and gesture for more straightforward ones. In this work, we examine when users choose to use speech, gesture, or both for the task of browsing the web on a TV in their living room, and identify common speech and gesture interactions for a set of fifteen browser functions, as well as discussing users' perceptions of the benefits and drawbacks of each modality.…”

Section: End-user Elicitation Studiesmentioning

confidence: 99%

Web on the wall

Morris

2012

Proceedings of the 2012 ACM International Conference on Interactive Tabletops and Surfaces

119

View full text Add to dashboard Cite

New sensing technologies like Microsoft's Kinect provide a low-cost way to add interactivity to large display surfaces, such as TVs. In this paper, we interview 25 participants to learn about scenarios in which they would like to use a web browser on their living room TV. We then conduct an interaction-elicitation study in which users suggested speech and gesture interactions for fifteen common web browser functions. We present the most popular suggested interactions, and supplement these findings with observational analyses of common gesture and speech conventions adopted by our participants. We also reflect on the design of multimodal, multi-user interaction-elicitation studies, and introduce new metrics for interpreting userelicitation study findings.

show abstract

Section: End-user Elicitation Studiesmentioning

confidence: 99%

Web on the wall

Morris

2012

Proceedings of the 2012 ACM International Conference on Interactive Tabletops and Surfaces

119

View full text Add to dashboard Cite

show abstract

“…The aforementioned study by Karl et al showed that using speech to issue commands to a word processing application, while using the keyboard for text entry and the mouse for direct manipulation, significantly sped up task time. Similarly, Mignot et al showed that the addition of spoken commands to direct manipulation (via a touchpad) greatly reduced the task performance times of their subjects [13].…”

Section: Introductionmentioning

confidence: 93%

A comparison of voice controlled and mouse controlled web browsing

Christian

Kules

Shneiderman

et al. 2000

Proceedings of the Fourth International ACM Conference on Assistive Technologies

View full text Add to dashboard Cite

show abstract

“…More recently, freehand interaction has been frequently explored as a modality for interacting with large vertical displays [11,18,37]. Multimodal interaction frequently leverages physical gestures alongside other input modalities [23,38], and toolkits have been developed to simplify the design and deployment of gesture sets [4,13].…”

Section: Designing Motion Gesture Inputmentioning

confidence: 99%

Effect of Motion-Gesture Recognizer Error Pattern on User Workload and Behavior

Katsuragawa

Kamal

Lank

2017

Proceedings of the 22nd International Conference on Intelligent User Interfaces

View full text Add to dashboard Cite

Bi-level thresholding is a motion gesture recognition technique that mediates between false positives, and false negatives by using two threshold levels: a tighter threshold that limits false positives and recognition errors, and a looser threshold that prevents repeated errors (false negatives) by analyzing movements in sequence. In this paper, we examine the effects of bi-level thresholding on the workload and acceptance of endusers. Using a wizard-of-Oz recognizer, we hold recognition rates constant and adjust for fixed versus bi-level thresholding. Given identical recognition rates, we show that systems using bi-level thresholding result in significant lower workload scores on the NASA-TLX and accelerometer variance. Overall, these results argue for the viability of bi-level thresholding as an effective technique for balancing between false positives, recognition errors and false negatives.

show abstract

An experimental study of future “natural” multimodal human-computer interaction

Abstract: In order to study users' spontaneous formulation of commands in the context of multimodal human-computer interaction (HCI), we conducted a Wizard of Oz experiment

Cited by 28 publications

References 3 publications

Web on the wall

Web on the wall

A comparison of voice controlled and mouse controlled web browsing

Effect of Motion-Gesture Recognizer Error Pattern on User Workload and Behavior

Contact Info

Product

Resources

About