论文信息 - Concurrent Collaborative Captioning

Concurrent Collaborative Captioning

Captioned text transcriptions of the spoken word can benefit hearing impaired people, non native speakers, anyone if no audio is available (e.g. watching TV at an airport) and also anyone who needs to review recordings of what has been said (e.g. at lectures, presentations, meetings etc.) In this paper, a tool is described that facilitates concurrent collaborative captioning by correction of speech recognition errors to provide a sustainable method of making videos accessible to people who find it difficult to understand speech through hearing alone. The tool stores all the edits of all the users and uses a matching algorithm to compare users’ edits to check if they are in agreement.

Mike Wald

[1] Jonathan G. Fiscus,et al. The Rich Transcription 2005 Spring Meeting Recognition Evaluation , 2005, MLMI.

[2] Wayne H. Ward,et al. Speech recognition , 1997 .

[3] Chris Callison-Burch,et al. Cheap, Fast and Good Enough: Automatic Speech Recognition with Non-Expert Transcription , 2010, NAACL.

[4] Sara H. Basson,et al. Speech recognition in university classrooms: liberated learning project , 2002, Assets '02.

[5] James R. Glass,et al. A Transcription Task for Crowdsourcing with Automatic Quality Control , 2011, INTERSPEECH.

[6] Mike Wald. Crowdsourcing correction of speech recognition captioning errors , 2011, W4A.

[7] Brian Kingsbury,et al. The IBM Attila speech recognition toolkit , 2010, 2010 IEEE Spoken Language Technology Workshop.

[8] Mike Wald. Synote: Designed for all Advanced Learning Technology for Disabled and Non-Disabled People , 2010, 2010 10th IEEE International Conference on Advanced Learning Technologies.