Presentation 2012-12-06
Effective Captioning Method by Using Croud-Sourcing Approach
Reiko Nagatsuma, Kentrou Fukuda, Yoshitomo Yaginuma, Yoko Hirose,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Creating captions helps hearing-impaired people be more confident about their comprehension of videos. Although the leading edge of captioning is currently focused on broadcast videos, captions for most Internet multimedia and videos are rare and hearing-impaired people have cannot access this information, even though it is used in many fields, such as education, news, and entertainment. The demand for captions is exploding, but the supply remains limited. To create more captions for multimedia content, we need tools to create the captions more efficiently. Our new captioning system uses crowd sourcing for the audio transcription work, which is time and labor intensive. Then more skilled workers and experts can concentrate on checking the sentences, adjusting the display timing, and improving the text. This system makes it possible to simultaneously improve the quality and efficiency of the captioning work. Our experimental trials show how well our crowd sourcing technique works, and also how it is affected by speech recognition technology.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Captioning / Crowd-Sourcing / Accessibility / Automated Speech Recognition
Paper # WIT2012-25
Date of Issue

Conference Information
Committee WIT
Conference Date 2012/11/29(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Well-being Information Technology(WIT)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Effective Captioning Method by Using Croud-Sourcing Approach
Sub Title (in English)
Keyword(1) Captioning
Keyword(2) Crowd-Sourcing
Keyword(3) Accessibility
Keyword(4) Automated Speech Recognition
1st Author's Name Reiko Nagatsuma
1st Author's Affiliation IBM Research()
2nd Author's Name Kentrou Fukuda
2nd Author's Affiliation IBM Research
3rd Author's Name Yoshitomo Yaginuma
3rd Author's Affiliation The Open University of Japan
4th Author's Name Yoko Hirose
4th Author's Affiliation The Open University of Japan
Date 2012-12-06
Paper # WIT2012-25
Volume (vol) vol.112
Number (no) 336
Page pp.pp.-
#Pages 6
Date of Issue