Using Avatars for Improving Speaker Identification in Captioning

Authors:
Quoc V. Vy;Deborah I. Fels
Affiliations:
Ryerson University, Toronto, Canada M5B 2K3;Ryerson University, Toronto, Canada M5B 2K3
Venue:
INTERACT '09 Proceedings of the 12th IFIP TC 13 International Conference on Human-Computer Interaction: Part II
Year:
2009

Citing 2
Cited 1

Participatory It Design: Designing for Business and Workplace Realities

Participatory It Design: Designing for Business and Workplace Realities
COVER STORY: Pencils before pixels: a primer in hand-generated sketching

interactions - Pencils before pixels: a primer in hand-generated sketching

Using placement and name for speaker identification in captioning

ICCHP'10 Proceedings of the 12th international conference on Computers helping people with special needs: Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Captioning is the main method for accessing television and film content by people who are deaf or hard-of-hearing. One major difficulty consistently identified by the community is that of knowing who is speaking particularly for an off screen narrator. A captioning system was created using a participatory design method to improve speaker identification. The final prototype contained avatars and a coloured border for identifying specific speakers. Evaluation results were very positive; however participants also wanted to customize various components such as caption and avatar location.