DSpace
 

Researchspace >
General science, engineering & technology >
General science, engineering & technology >
General science, engineering & technology >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10204/5770

Title: Collecting and evaluating speech recognition corpora for 11 South African languages
Authors: Badenhorst, J
Van Heerden, C
Davel, M
Barnard, E
Keywords: South Afrcan languages
Lwazi corpus
Automatic speech recognition (ASR)
Speech recognition
Speech recognition evaluation
Issue Date: Aug-2011
Publisher: Springer Science+Business Media B.V.
Citation: Badenhorst, J, Van Heerden, C, Davel, M and Barnard, E. 2011. Collecting and evaluating speech recognition corpora for 11 South African languages. Language Resources and Evaluation, vol. 45(3), pp 289-309
Series/Report no.: Workflow;8149
Abstract: The authors describe the Lwazi corpus for automatic speech recognition (ASR), a new telephone speech corpus which contains data from the eleven official languages of South Africa. Because of practical constraints, the amount of speech per language is relatively small compared to major corpora in world languages, and they report on their investigation of the stability of the ASR models derived from the corpus. They also report on phoneme distance measures across languages, and describe initial phone recognisers that were developed using this data. They find that a surprisingly small number of speakers (fewer than 50) and around 10 to 20 hours of speech per language are sufficient for the purposes of acceptable phone-based recognition.
Description: Copyright: 2011 Springer-Verlag. This is the pre-print version of the work. The definitive version is published in Language Resources and Evaluation, vol. 45(3), pp 289-309
URI: http://www.springerlink.com/content/m772051343jg875k/fulltext.pdf
http://hdl.handle.net/10204/5770
ISSN: 1574-020X
1574-0218
Appears in Collections:Human language technologies
General science, engineering & technology

Files in This Item:

File Description SizeFormat
Badenhorst1_2011.pdf369.42 kBAdobe PDFView/Open
View Statistics

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback