Accessibility, transcription, and access everywhere

IBM Systems Journal

Volumn 44, Issue 3, 2005, Pages 589-603

  Bain, Keith ^a   Basson, Sara ^b   Faisman, Alexander ^b   Kanevsky, Dimitri ^b  

^a SAINT MARY S UNIVERSITY   (Canada)

^b IBM T J WATSON RESEARCH CENTER   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

AUDITION; HANDICAPPED PERSONS; HUMAN COMPUTER INTERACTION; SPEECH RECOGNITION; USER INTERFACES;

AUDIO ACCESS; DEAF ACCESSIBILITY; SIGN INTERPRETATION; TRANSCRIPTION;

USABILITY ENGINEERING;

EID: 23744482680     PISSN: 00188670     EISSN: None     Source Type: Journal    
DOI: 10.1147/sj.443.0589     Document Type: Article

References (21)

1. P. F. Adams and V. Benson, "Current Estimates from the National Health Interview Survey, 1991," Vital and Health Statistics, Series No. 10, National Center for Health Statistics (1992).
2. The choice of whether to provide stenography or sign interpretation is not obvious, and there are strong user needs and preferences that extend beyond the scope of this paper. ViaScribe-led projects have, to date, focused on providing textual support for persons who are deaf or hard of hearing. There is a large community of deaf users, however, for whom sign language is the preferred method of communication. Some exploratory work is underway to include a "signing window" as an optional feature in ViaScribe displays.
3. The relative costs of stenography and signing are discussed in G. D. Robson, Working with Sign Interpreters (July 1999), http://captioning.robson.org/articles/captioncart/caption-cart9907.html. Although the cost per hour of signing is less than the cost of captioning, signers require more frequent breaks, and a four-hour meeting, therefore, requires more than one signer, but only one captioner.
4. A history of speech recognition improvements and continuing challenges is described in D. Pallet, A Look at NIST's Benchmark ASR Tests: Pash Present, Future, National Institute of Standards (2003), http://www.nist.-gov/speech/history/pdf/NIST_benchmark_ASRtests_2003.pdf.
5. A description of netCAPTION can be found at the Caption First Web site, http://www.captionfirst.com/overview.htm#internet.
6. A. Lambourne, J. Hewitt, C. Lyon, and S. Warren, "Speech-Based Real-Time Subtitling Services," International Journal of Speech Technology 7, No. 4, 269-279 (2004).
7. P. Francis and M. Stinson, "The C-Print Speech-to-Text System for Communication Access and Learning," Proceedings of CSUN's 18th Annual International Conference on Technology anal Persons With Disabilities (CSUN 2003), Los Angeles, CA, March 17-22, 2003, http://www.csun.edu/cod/conf/2003/proceedings/157.htm.
8. D. A. Leitch, Canadian Universities: The Status of Persons with DisabiIities, Saint Mary's University, Halifax, Nova Scotia, Canada, http://www.smu.ca/administration/studentservices/atlcentr/annual/ status2.doc.
9. D. Leitch and K. Bain, "The Liberated Learning Project: Improving Access for Persons with Disabilities in Higher Education using Speech Recognition Technology," Proceedings of The AVIOS 2000 Speech Technology and Applications Expo, San Jose, CA, May 23-24, 2000, Sara Basson, Editor, Applied Voice Input/Output Society, San Jose, CA (2000), pp. 83-86.
10. Synchronized Multimedia, World Wide Web Consortium, http://www.w3.org/ AudioVideo/.
11. D. Leitch and T. MacMillan, Liberated Learning Project: Improving Access for Persons with Disabilities in Higher Education Using Speech Recognition Technology; Year II Report, Saint Mary's University, Halifax, Nova Scotia, Canada (2001).
12. R. Stuckless, Assessing the Word Accuracy of Text Produced from an Instructor' s Use of ASR in the College Classroom, Saint Mary's University, Halifax, Nova Scotia, Canada (2000).
13. R. Stuckless, First Comments on LLP Accuracy/Bench-marking Activities, Saint Mary's University, Halifax, Nova Scotia, Canada (2001).
14. Data obtained from experienced editors for the LLP.
15. K. Bain and D. Paez, "Speech Recognition in Lecture Theatres," Proceedings of the Eighth Australian International Conference on Speech Science and Technology (SST-2000), Australian National University, Canberra, December 5-7, 2000.
16. The cost of captioning a one-hour video is $500-$1000. See H. Kaplan, J. Mahshie, M. J. Moseley, B. Singer, and E. Winston, Design of Effective Media, Materials and Technology for Deaf and Hard-of-Hearing Students, National Center to Improve the Tools of Educators, University of Oregon, Eugene, OR.
17. D. Ferrucci and A. Lally, "Building an Example Application with the Unstructured Information Management Architecture," IBM Systems Journal 143, No. 3, 445-475 (2004).
18. T. Götz and O. Suhre, "Design and Implementation of the UIMA Common Analysis System," IBM Systems Journal 43, No. 3, 476-489 (2004).
19. D. Kanevsky, S. H. Basson, and P. G. Fairweather, Integration of Speech Recognition and Stenographic Services for Improved ASR Training, U.S. Patent No. 6,832,189 (December 14, 2004).
20. A. Coursand-Moreau, F. Crepy, and F. Destombes, "Lipcom: An IBM Research Project to Help Reception of Speech by Deaf Persons," Proceedings of the International Conference on Computers Helping People with Special Needs (ICCHP 2000), Karlsruhe, Germany, July 17-21, 2000, pp. 127-134.
21. S. Basson, A. Faisman, W. Ferre, J. Ghez, D. Kanevsky, and J. Quinery, "Lipcom: Speech Recognition as a Teaching Aid for Hearing-Impaired Children," Proceedings of the Conference and Workshop on Assistive Technologies for Vision and Hearing Impairment (CVHI'2002), Granada, Spain, August 6-9, 2002.