GENERAL ENQUIRIES: Tel: + 27 12 841 2911 | Email: callcentre@csir.co.za

Browsing Human language technologies by Title

Sort by: Order: Results:

  • Van't Wout, Magdalena C; Pieterse, Heloise; Ball, Shaun V (IEEE, 2019-10)
    An overview of the literature on military-related stress confirms that stress remains part of the deployed soldier’s life, whether it relates to concerns about his family back home, the nature of the military environment, ...
  • Butgereit, L (Assciation for Mathematics Education of South Africa, 2007-07)
    Homework is a necessary evil in the path of learning mathematics at school. Mathematics homework is traditionally seen as difficult and boring. In the case of difficult homework, “math clubs” and “math extra lessons” are ...
  • Butgereit, L (2007-04)
    It is common cause that the average mathematics mark among high school learners in South Africa has declined. Traditional “math clubs” and “math extra lessons” often do not work because of a number of reasons including 1) ...
  • Van der Walt, Christiaan M; Barnard, E (18th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), 2007-11)
    The authors study the relationship between the properties of data and classifier performance. Data measures are employed to characterise classification problems and it is shown that these data measures successfully capture ...
  • Chamber of Mines, South Africa (Chamber of Mines Services, 1978)
    In simple terms Fanakalo means 'like this'. Fanakalo originated in the sugar industry of KwaZulu Natal as a result of Indians trying to learn English and Zulu at the same time. The language spread across the boarders of ...
  • Botha, Adèle; Van Greunen, D; Herselman, Martha E (2010-10)
    Applying a Mobile Human Computer Interaction (MHCI) view to the domain of education using Mobile Learning (Mlearning), the research outlines its understanding of the influences and effects of different interactions on the ...
  • Botha, Adèle; Calteaux, K; Herselman, Martha E; Grover, AS; Barnard, E (Karlstad University Press, 2012-02)
    The purpose of this paper is to provide a “Mobile User Experience Framework for Voice services.” The rapid spread of mobile cellular technology within Africa has made it a prime vehicle for accessing services and content. ...
  • Wilken, I; De Wet, Febe; Taljard, E (ISCA, 2015-09)
    Communication plays a vital role in everyday life and in some situations multilingual communication is a necessity. The South African constitution recognises 11 official languages. Multilingual communication therefore ...
  • Coetzee, L; Viviers, I; Barnard, E (PRASA 2009, 2009-12)
    Multi-modal human computer interfaces are becoming increasingly widespread, building on more capable and affordable devices along with advances in helper applications utilising advanced pattern recognition. These interfaces ...
  • Plauché, M; De Waal, A; Sharma Grover, A; Gumede, T (University of Southern California, Annenberg School for Communication & Journalism, 2010)
    Successful ICT projects depend on complex, interrelated sociological and technical factors for which there are no standard theoretical framework for prediction or analysis. Morphological analysis is a problem-solving method ...
  • Feld, M; Barnard, E; Van Heerden, C; Muller, C (IEEE, 2009-12)
    Multilinguality represents an area of significant opportunities for automatic speech-processing systems: whereas multilingual societies are commonplace, the majority of speechprocessing systems are developed with a single ...
  • Tönsing, KM; Van Niekerk, K; Schlunz, Georg I; Wilken, Ilana (AOSIS, 2019-04)
    Background: Augmentative and alternative communication (AAC) can assist persons with complex communication needs to communicate competently with a variety of communication partners in a variety of contexts. However, AAC ...
  • Van Dyk, E; Barnard, E (18th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA), 2007-11)
    The authors investigate the use of naive Bayesian classifiers for multinomial feature spaces and derive error estimates for these classifiers. The error analysis is done by developing a mathematical model to estimate the ...
  • De Waal, AJ; Louis, AL; Venter, JP (2006-10)
    Named Entity Recognition (NER) is the process of identifying occurrences of words or expressions as belonging to a particular category of a Named Entity (NE).The aim of the project was to test the feasibility of a probabilistic ...
  • Butgereit, LL (Cape Peninsula University of Technology, 2009-09)
    The National Accessibility Portal is a web respository of information for South Africans living with disabilities. Information stored on the portal include copies of legislation applicable to people with disabilities, lists ...
  • Barnard, E; Davel, MH; Van Heerden, C; De Wet, Febe; Badenhorst, J (2014-05)
    The NCHLT speech corpus contains wide-band speech from approximately 200 speakers per language, in each of the eleven of cial languages of South Africa. We describe the design and development processes that were undertaken ...
  • Louw, Johannes A (Ruzica Piskac, 2019-12)
    Recent work in sequence-to-sequence neural networks with attention mechanisms, such as the Tacotron 2 and DCTTS architectures, have brought on substantial naturalness improvements in synthesised speech. These architectures ...
  • McAlister, BN; Steyn, JL (IEEE, 2012-08)
    The potential applicability of established new product development processes to information and communications technology (ICT)-for-development projects is investigated. The demand for ICT solutions to serve numerous ...
  • Molapo, R; Barnard, E (Pattern Recognition Association of South Africa, 2014-11)
    The purpose of this paper is to address the challenges and describe step-by-step solutions faced when developing an automatic speech recognition system in multilingual societies. We give a brief statistical analysis of the ...
  • Govender, Avashna; De Wet, Febe (IEEE, 2016-12)
    Building synthetic child voices is considered a difficult task due to the challenges associated with data collection. As a result, speaker adaptation in conjunction with Hidden Markov Model (HMM)-based synthesis has become ...

Search ResearchSpace


Advanced Search

Browse

My Account