Adaptive time windows for real-time crowd captioning

Authors:
Matthew J. Murphy;Christopher D. Miller;Walter S. Lasecki;Jeffrey P. Bigham
Affiliations:
University of Rochester, Rochester, USA;University of Rochester, Rochester, USA;University of Rochester, Rochester, USA;University of Rochester, Rochester, USA
Venue:
CHI '13 Extended Abstracts on Human Factors in Computing Systems
Year:
2013

Citing 5
Cited 1

VizWiz: nearly real-time answers to visual questions

UIST '10 Proceedings of the 23nd annual ACM symposium on User interface software and technology
Real-time crowd control of existing interfaces

Proceedings of the 24th annual ACM symposium on User interface software and technology
Crowds in two seconds: enabling realtime crowd-powered interfaces

Proceedings of the 24th annual ACM symposium on User interface software and technology
Real-time captioning by groups of non-experts

Proceedings of the 25th annual ACM symposium on User interface software and technology
Online quality control for real-time crowd captioning

Proceedings of the 14th international ACM SIGACCESS conference on Computers and accessibility

Accessibility Evaluation of Classroom Captions

ACM Transactions on Accessible Computing (TACCESS)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Real-time captioning provides deaf and hard of hearing users with access to live spoken language. The most common source of real-time captions are professional stenographers, but they are expensive (up to $200/hr). Recent work shows that groups of non-experts can collectively caption speech in real-time by directing workers to different portions of the speech and automatically merging the pieces together. This work uses 'one size fits all' segment durations regardless of an individual worker's ability or preferences. In this paper, we explore the effect of adaptively scaling the amount of content presented to each worker based on their past and recent performance. For instance, giving fast typists longer segments and giving workers shorter segments as they fatigue. Studies with 24 remote crowd workers, using ground truth in segment calculations, show that this approach improves average coverage by over 54%, and F1 score (harmonic mean) by over 44%.