dc.contributor.author | Badenhorst, Jaco | en_US |
dc.contributor.author | Van Heerden, Charl | en_US |
dc.contributor.author | Barnard, Etienne | en_US |
dc.contributor.author | Davel, Marelie H. | |
dc.date.accessioned | 2015-01-30T09:21:54Z | |
dc.date.available | 2015-01-30T09:21:54Z | |
dc.date.issued | 2011 | en_US |
dc.identifier.citation | Badenhorst, 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. [http://link.springer.com/journal/10579] | en_US |
dc.identifier.issn | 0921-2973 | |
dc.identifier.issn | 1572-9761 (O) | |
dc.identifier.uri | http://hdl.handle.net/10394/13095 | |
dc.description.abstract | We 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.description.uri | http://dx.doi.org/10.1007/s10579-011-9152-1 | |
dc.description.uri | http://link.springer.com/article/10.1007/s10579-011-9152-1 | |
dc.language | en | |
dc.publisher | Springer | |
dc.subject | Speech recognition | |
dc.subject | Lwazi corpus | |
dc.subject | Resource-scarce languages | |
dc.subject | South African languages | |
dc.title | Collecting and evaluating speech recognition corpora for 11 South African languages | en_US |
dc.type | Article | |
dc.contributor.researchID | 11539151 - Van Heerden, Carel Jacobus | |
dc.contributor.researchID | 23607955 - Davel, Marelie Hattingh | |
dc.contributor.researchID | 21021287 - Barnard, Etienne | |