Miss-Delectable
New Member
- Joined
- Apr 18, 2004
- Messages
- 17,160
- Reaction score
- 7
WGBH Works with Nuance Communications, Inc. on Effort to Improve the Quality of Live News Captioning - MarketWatch
Nuance Communications, Inc. today announced that it is working in collaboration with WGBH's National Center for Accessible Media (NCAM) on a U.S. Department of Education-funded Project to develop a prototype system to automatically assess accuracy of real-time captions for live news programming. The system will identify and weigh the impact of different kinds of errors in closed captions.
The variations in quality and accuracy of real-time captioning have long been a concern to people who are deaf or hard of hearing. Captioned news in particular can be a lifeline to viewers who cannot hear well enough to follow program audio, a lifeline only as strong as the captioning is accurate. Live, or real-time captions are most often produced by specially trained court reporters, called stenocaptioners, who use a phonetic keyboard attached to a computerized dictionary to translate spoken words into text in a matter of a few seconds. National consumer advocacy organizations have petitioned the FCC to consider adding a standard of caption quality to existing mandates for quantity of captioning on television.
An early activity of NCAM's "Caption Accuracy Metrics" Project was the design and launch of a web-based national consumer survey of television news caption viewers. Respondents were asked to read sample captions and identify error types that make captions hard to follow. Basic real-time captioning error types are word substitutions, deletions (dropped words or omissions) and insertions (addition of words not spoken).
WGBH is working with Nuance Communications, a leader in speech solutions, to develop customized language processing, data analysis, and benchmarking tools for the Project. Nuance is leveraging its Dragon NaturallySpeaking speech recognition technology to develop these tools in order to quantify and further analyze the captioning data that is being gathered. Nuance's work is integral to the Project's development of a final prototype tool that will enable tracking of audio and captioning
Nuance Communications, Inc. today announced that it is working in collaboration with WGBH's National Center for Accessible Media (NCAM) on a U.S. Department of Education-funded Project to develop a prototype system to automatically assess accuracy of real-time captions for live news programming. The system will identify and weigh the impact of different kinds of errors in closed captions.
The variations in quality and accuracy of real-time captioning have long been a concern to people who are deaf or hard of hearing. Captioned news in particular can be a lifeline to viewers who cannot hear well enough to follow program audio, a lifeline only as strong as the captioning is accurate. Live, or real-time captions are most often produced by specially trained court reporters, called stenocaptioners, who use a phonetic keyboard attached to a computerized dictionary to translate spoken words into text in a matter of a few seconds. National consumer advocacy organizations have petitioned the FCC to consider adding a standard of caption quality to existing mandates for quantity of captioning on television.
An early activity of NCAM's "Caption Accuracy Metrics" Project was the design and launch of a web-based national consumer survey of television news caption viewers. Respondents were asked to read sample captions and identify error types that make captions hard to follow. Basic real-time captioning error types are word substitutions, deletions (dropped words or omissions) and insertions (addition of words not spoken).
WGBH is working with Nuance Communications, a leader in speech solutions, to develop customized language processing, data analysis, and benchmarking tools for the Project. Nuance is leveraging its Dragon NaturallySpeaking speech recognition technology to develop these tools in order to quantify and further analyze the captioning data that is being gathered. Nuance's work is integral to the Project's development of a final prototype tool that will enable tracking of audio and captioning