A readability evaluation of real-time crowd captions in the classroom

Raja S. Kushalnagar, Walter S. Lasecki, Jeffrey P. Bigham
2012 Proceedings of the 14th international ACM SIGACCESS conference on Computers and accessibility - ASSETS '12  
Deaf and hard of hearing individuals need accommodations that transform aural to visual information, such as tran scripts generated in real-time to enhance their access to spoken information in lectures and other live events. Pro fessional captionists's transcripts work well in general events such as community, administrative or legal meetings, but is often perceived as not readable enough in specialized con tent events such as higher education classrooms. Profes sional captionists with
more » ... ce in specialized content ar eas are scarce and expensive. Commercial automatic speech recognition (ASR) software transcripts are far cheaper, but is often perceived as unreadable due to ASR's sensitivity to accents, background noise and slow response time. We eval uate the readability of a new crowd captioning approach in which captions are typed collaboratively by classmates into a system that aligns and merges the multiple incom plete caption streams into a single, comprehensive real-time transcript. Our study asked 48 deaf and hearing readers to evaluate transcripts produced by a professional captionist, automatic speech recognition software and crowd captioning software respectively and found the readers preferred crowd captions over professional captions and ASR.
doi:10.1145/2384916.2384930 dblp:conf/assets/KushalnagarLB12 fatcat:s44b7eitf5clvmk4kzagoihi6u