South Africa has eleven official languages, ten of which are considered “resource-scarce”. For these languages, even basic linguistic resources required for the development of speech technology systems can be difficult or impossible to obtain. In this thesis, the process of developing Spoken Language Identification (S-LID) systems in resource-scarce environments is investigated. A Parallel Phoneme Recognition followed by Language Modeling (PPR-LM) architecture is utilized and three specific scenarios are investigated: (1) incomplete resources, including the lack of audio transcriptions and/or pronunciation dictionaries; (2) inconsistent resources, including the use of speech corpora that are unmatched with regard to domain or channel characteristics; and (3) poor quality resources, such as wrongly labeled or poorly transcribed data. Each situation is analysed, techniques defined to mitigate the effect of limited or poor quality resources, and the effectiveness of these techniques evaluated experimentally. Techniques evaluated include the development of orthographic tokenizers, bootstrapping of transcriptions, filtering of low quality audio, diarization and channel normalization techniques, and the human verification of miss-classified utterances. The knowledge gained from this research is used to develop the first S-LID system able to distinguish between all South African languages. The system performs well, able to differentiate among the eleven languages with an accuracy of above 67%, and among the six primary South African language families with an accuracy of higher than 80%, on segments of speech of between 2s and 10s in length. AFRIKAANS : Suid-Afrika het elf amptelike tale waarvan tien as hulpbron-skaars beskou word. Vir die tien tale kan selfs die basiese hulpbronne wat benodig word om spraak tegnologie stelsels te ontwikkel moeilik wees om te bekom. Die proses om ‘n Gesproke Taal Identifisering stelsel vir hulpbron-skaars omgewings te ontwikkel, word in hierdie tesis ondersoek. ‘n Parallelle Foneem Herkenning gevolg deur Taal Modellering argitektuur word ingespan om drie spesifieke moontlikhede word ondersoek: (1) Onvolledige Hulpbronne, byvoorbeeld vermiste transkripsies en uitspraak woordeboeke; (2) Teenstrydige Hulpbronne, byvoorbeeld die gebruik van spraak data-versamelings wat teenstrydig is in terme van kanaal kenmerke; en (3) Hulpbronne van swak kwaliteit, byvoorbeeld foutief geklasifiseerde data en klank opnames wat swak getranskribeer is. Elke situasie word geanaliseer, tegnieke om die negatiewe effekte van min of swak hulpbronne te verminder word ontwikkel, en die bruikbaarheid van hierdie tegnieke word deur middel van eksperimente bepaal. Tegnieke wat ontwikkel word sluit die ontwikkeling van ortografiese ontleders, die outomatiese ontwikkeling van nuwe transkripsies, die filtrering van swak kwaliteit klank-data, klank-verdeling en kanaal normalisering tegnieke, en menslike verifikasie van verkeerd geklassifiseerde uitsprake in. Die kennis wat deur hierdie navorsing bekom word, word gebruik om die eerste Gesproke Taal Identifisering stelsel wat tussen al die tale van Suid-Afrika kan onderskei, te ontwikkel. Hierdie stelsel vaar relatief goed, en kan die elf tale met ‘n akkuraatheid van meer as 67% identifiseer. Indien daar op die ses taal families gefokus word, verbeter die persentasie tot meer as 80% vir segmente wat tussen 2 en 10 sekondes lank. Copyright / Dissertation (MEng)--University of Pretoria, 2010. / Electrical, Electronic and Computer Engineering / unrestricted

Text in Afrikaans / In this study essential guidelines are given to Foundation Phase educators for the teaching of basic English concepts to English second language learners. Die research design is explained and recommendations are made. The following underlying problems, which were encountered in the research recommendation, are identified and discussed: Learning barriers with specific reference to English as a second language. The causes of learning barriers which include the discussion of intrinsic and extrinsic factors. Educator training is lacking and educators do not have the necessary knowledge and skills to teach basic concepts in English to second language learners. The necessity and advantages of timeous identification of barriers to learning to ensure that basic concepts are taught. The study was concluded with practical guidelines to reinforce basic concepts in learners in the Foundation Phase who are taught in English as a second language. Recommendations were made to parents, educators and the Department of Education. / In die studie word riglyne aan Grondslagfase-onderwysers gegee vir die onderrig van basiese konsepte in Engels aan Engels tweedetaalleerders. Hierdie basiese konsepte is noodsaaklik vir vordering in die Grondslagfase. Die navorsingontwerp verduidelik en aanbevelings gemaak. Die volgende sub-probleme wat onderliggend is aan die navorsingsvoorstel is geïdentifiseer en bespreek, naamlik: Struikelblokke tot leer met spesifieke verwysing na Engels as tweedetaal. Die oorsake wat lei tot struikelblokke tot leer waaronder intrinsieke en ekstrinsieke faktore word bespreek. Onderwyseropleiding is onvoldoende en onderwysers beskik nie oor die kennis en vaardighede om basiese konsepte in Engels aan Engels tweedetaalleerders te onderrig nie. Die noodsaaklikheid van vroeë identifisering en die voordele verbonde aan vroegtydige identifisering van struikelblokke tot leer om te verseker dat basiese konsepte voldoende vasgelê word. Die studie is afgesluit met praktiese riglyne vir die vaslegging van basiese konsepte aan leerders in die Grondslagfase wat in Engels as tweede taal onderrig word. Aanbevelings is aan die ouers, onderwysers en die Departement van Onderwys gemaak. / Inclusive Education / M. Ed. (Inklusiewe Onderwys)

Abstracts in English, Afrikaans and Xhosa / The purpose of this study was to explore reading barriers of Foundation Phase learners in IsiXhosa Home Language in the Lady Frere district in the Eastern Cape Province (ECP). The qualitative single case study of one Junior Secondary school in the chosen district was studied. The empirical research was done through interviews with the teachers and lesson observations. The findings suggested that there was some concern with regards to the reading ability of learners in the District. The lack of parental involvement, high turnover of teachers, lack of training and support of teachers were identified as attributing factors to reading barriers of learners. Measures to address these factors were suggested. The measures included capacity building of teachers, parents or care givers of learners, and ways of retaining teachers in schools to reduce the high turnover of staff. In conclusion, it is anticipated that the findings and recommendations of this study will provide valuable contribution to the district officials to be able to address the teaching and learning gaps and empower and support both teachers and learners in the Eastern Cape Province. / Die doel van hierdie studie was om leeshindernisse van leerders in die Grondslagfase, met Xhosa as huistaal, in die Lady Frere distrik in die Oos-Kaap Provinsie te ondersoek. Die kwalitatiewe, enkele gevallestudie het die bestudering van een Junior Sekondêre skool in die gekose distrik behels. Die empiriese navorsing is gedoen deur onderhoude met die onderwysers te voer en deur waarnemings van lesse. Die bevindings dui daarop dat daar kommer bestaan oor die leesvermoë van leerders in die distrik. Afwesige ouerbetrokkenheid, die hoë omset van onderwysers en die gebrek aan voldoende opleiding en ondersteuning aan onderwysers word identifiseer as die moontlike oorsake van leeshindernisse van leerders. Maatreëls om die faktore wat leeshindernisse veroorsaak aan te spreek, is voorgestel. Die maatreëls behels onder meer kapasiteitsbou van onderwysers, ouers of versorgers van leerders, asook maniere om onderwysers in skole te behou en sodoende die hoë personeelomset te verminder. Ten slotte, die verwagting is dat die bevindings en aanbevelings van hierdie studie ‘n waardevolle bydrae aan die distriksbeamptes sal lewer om die leemtes vir voldoende onderrig en leer te kan aanpak en sodoende beide onderwysers en leerders in die Oos- Kaap te bemagtig en te ondersteun. / Injongo yoluphando yayikukuphonononga izithintelo kufunda zamabanga aphantsi kulwimi lwasekhaya lwesiXhosa kwisithili saseCacadu kwiphondo laseMpuma-Koloni. Kwaphononongwa isifundo secala elinye elinoqeqesho kwisikiolo samabanga aphakathi kwisithili esikhethiweyo. Kwenziwa uphando olunamandla kusetyenziswa udliwanondlebe nootitshala kunye nokujonga. Iziphumo zabonisa ukuba kukho ukuxhalaba ngendlela abafundi besithili esikhethiweyo babefunda ngayo. Oko kwakudalwa kukungazibandakanyi kwabazali emfundweni yabantwana babo, ukutshintsha nokushiya kootitshala izikolo nesebe lezemfundo ngokubanzi nokunqongophala koqeqesho nenkxaso yootitshala. Kwacetyiswa amadondolo okulungisa imiba echaphazela iingxaki zokufunda . Lamadondolo ayecebisa ukuba kujongwane nemiceli mingeni eyayisele iboniwe, enje ngophuhliso lweetitsshala, abazali okanye abagcini bantwana, iindlela zokugcina abasebenzi ezikolweni, ukunciphisa ukutshintsha izikolo nokuyeka ukufundisa kootitshala. Ukuphetha, kuyabonakala ukuba iziphumo nezindululo zoluphando zizakuba negalelo elingathethekiyo kumagosa ezemfundo. Loo nto iyakuwanceda amagosa lawo akwazi ukuqaphela nokuqubisana nezikhewu ekufundeni, baphuhlise baxhase ootitshala nabantwana kwiPhondo leMpuma-Koloni. / Inclusive Education / M. Ed. (Inclusive Education)