Correcting Automatic Speech Recognition Errors in Real Time
Correcting Automatic Speech Recognition Errors in Real Time
Lectures can be digitally recorded and replayed to provide multimedia revision material for students who attended the class and a substitute learning experience for students unable to attend. Deaf and hard of hearing people can find it difficult to follow speech through hearing alone or to take notes while they are lip-reading or watching a sign-language interpreter. Synchronising the speech with text captions can ensure deaf students are not disadvantaged and assist all learners to search for relevant specific parts of the multimedia recording by means of the synchronised text. Automatic Speech Recognition has been used to provide real-time captioning directly from lecturers’ speech in classrooms but it has proved difficult to obtain accuracy comparable to stenography. This paper describes the development, testing and evaluation of a system that enables editors to correct errors in the captions as they are created by Automatic Speech Recognition and makes suggestions for future possible improvements.
accessibility, multimedia, automatic speech recognition, captioning, real-time editing
1-15
Wald, M
90577cfd-35ae-4e4a-9422-5acffecd89d5
Boulain, P
61a50e56-d076-4419-9ac9-a99006c4a61a
Bell, J
63af40e1-5f46-437b-bc97-2dbeaf685e3f
Doody, K
90dbe547-e6bc-4c5b-ab12-1d26187311d4
Gerrard, J
513ee649-4caa-4c03-9e89-869f288f68e7
Damper, B
5d303d77-ac1a-4f39-a7be-98ece54996d4
2007
Wald, M
90577cfd-35ae-4e4a-9422-5acffecd89d5
Boulain, P
61a50e56-d076-4419-9ac9-a99006c4a61a
Bell, J
63af40e1-5f46-437b-bc97-2dbeaf685e3f
Doody, K
90dbe547-e6bc-4c5b-ab12-1d26187311d4
Gerrard, J
513ee649-4caa-4c03-9e89-869f288f68e7
Damper, B
5d303d77-ac1a-4f39-a7be-98ece54996d4
Wald, M, Boulain, P, Bell, J, Doody, K and Gerrard, J
,
Damper, B
(ed.)
(2007)
Correcting Automatic Speech Recognition Errors in Real Time.
International Journal of Speech Technology, 10 (1), .
Abstract
Lectures can be digitally recorded and replayed to provide multimedia revision material for students who attended the class and a substitute learning experience for students unable to attend. Deaf and hard of hearing people can find it difficult to follow speech through hearing alone or to take notes while they are lip-reading or watching a sign-language interpreter. Synchronising the speech with text captions can ensure deaf students are not disadvantaged and assist all learners to search for relevant specific parts of the multimedia recording by means of the synchronised text. Automatic Speech Recognition has been used to provide real-time captioning directly from lecturers’ speech in classrooms but it has proved difficult to obtain accuracy comparable to stenography. This paper describes the development, testing and evaluation of a system that enables editors to correct errors in the captions as they are created by Automatic Speech Recognition and makes suggestions for future possible improvements.
More information
Published date: 2007
Keywords:
accessibility, multimedia, automatic speech recognition, captioning, real-time editing
Organisations:
Web & Internet Science
Identifiers
Local EPrints ID: 262140
URI: http://eprints.soton.ac.uk/id/eprint/262140
PURE UUID: dfd011d2-a025-48ef-9fb9-707c090f39f8
Catalogue record
Date deposited: 24 Mar 2006
Last modified: 14 Mar 2024 07:06
Export record
Contributors
Author:
M Wald
Author:
P Boulain
Author:
J Bell
Author:
K Doody
Author:
J Gerrard
Editor:
B Damper
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics