Black South African English and Speech Technology Applications

Abstract

Hierdie artikel stel 'n lopende navorsings- en ontwikkelingsprojek in die veld van Menslike Taaltegnologie bekend, waarin daar op vyf van die amptelike tale van Suid-Afrika gefokus word. Die basiese komponente van 'n outomatiese informasieherwinningsisteem word uiteengesit met besondere verwysing na die tipes spraakdatabasisse wat in die Suid-Afrikaanse konteks ontwikkel moet word. Die posisie van Swart Suid-Afrikaanse Engels (SSAE) word bespreek en 'n eksperiment word beskryf waarin die outomatiese spraakherkenningsukses van twee vorme van SSAE bepaal word deur van intydse tegnologie gebruik te maak. Daar word geargumenteer dat die verkryging van SSAE-spraakdatabasisse nie net essensieel is vir tegnologieontwikkeling nie, maar ook 'n bydrae kan lewer tot die debat oor die moontlike bestaan van vorme van SSAE wat aan verskillende eerstetale gebonde is.

This article introduces a current research and development project in the field of Human Language Technologies which focuses on five of the official languages of South Africa. The basic components of an automatic information retrieval system are explicated with special reference to the types of speech databases that need to be developed in the South African context. The position of Black South African English (BSAE) is reviewed and an experiment is described in which the automatic speech recognition rate of two versions of BSAE were assessed, utilising state-of-the-art technology. It is argued that the acquisition of BSAE speech databases is not only imperative for technology development, but that it may also make a contribution towards the debate on the possible existence of first language-bound varieties of BSAE.