Show simple item record

dc.contributor.authorBadenhorst, Jacoen_US
dc.contributor.authorVan Heerden, Charlen_US
dc.contributor.authorBarnard, Etienneen_US
dc.contributor.authorDavel, Marelie H.
dc.identifier.citationBadenhorst, J. & Van Heerden, C., et al. 2011. Collecting and evaluating speech recognition corpora for 11 South African languages. Language resources and evaluation, 45(3):289-309. []en_US
dc.identifier.issn1572-9761 (O)
dc.description.abstractWe 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 we report on our investigation of the stability of the ASR models derived from the corpus. We also report on phoneme distance measures across languages, and describe initial phone recognisers that were developed using this data. We find that a surprisingly small number of speakers (fewer than 50) and around 10 to 20 h of speech per language are sufficient for the purposes of acceptable phone-based recognition.
dc.subjectSpeech recognition
dc.subjectLwazi corpus
dc.subjectResource-scarce languages
dc.subjectSouth African languages
dc.titleCollecting and evaluating speech recognition corpora for 11 South African languagesen_US
dc.contributor.researchID11539151 - Van Heerden, Carel Jacobus
dc.contributor.researchID23607955 - Davel, Marelie Hattingh
dc.contributor.researchID21021287 - Barnard, Etienne

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record