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

Browsing Human language technologies by Title

Sort by: Order: Results:

  • Van der Walt, Christiaan M; Barnard, E (2006-11)
    The relationship between the distribution of data, on the one hand, and classifier performance, on the other, for non-parametric classifiers has been studied. It is shown that predictable factors such as the available ...
  • Badenhorst, JAC; Davel, M (PRASA 2008, 2008-11)
    When developing speech recognition systems in resource-constrained environments, careful design of the training corpus can play an important role in compensating for data scarcity. One of the factors to consider relates ...
  • Davel, MH; Barnard, E (PRASA 2004, 2004-11)
    The authors define a novel g-to-p prediction algorithm that utilises the concept of a 'default phoneme': a grapheme which is realised as a specific phoneme significantly more often than as any other phoneme. They found ...
  • Casini, G; Meyer, T; Varzinczak, I (2018-10)
    In this paper we present what we believe to be the first systematic approach for extending the framework for defeasible entailment first presented by Kraus, Lehmann, and Magidor—the so-called KLM approach. Drawing on the ...
  • Marais, Laurette; Van Zijl, L (Open Publishing Association, 2017-09)
    Previously, self-verifying symmetric difference automata were defined and a tight bound of 2^n-1-1 was shown for state complexity in the unary case. We now consider the non-unary case and show that, for every n at least ...
  • Sharma Grover, A; Stewart, O; Lubensky, D (2009-11)
    In this paper, the authors address the issue of how to design IVR interfaces for the developing world. Against the backdrop of the following idiosyncratic observations including, the majority of users being either semi-literate ...
  • De Wet, Febe; De Waal, A; Van Huyssteen, GB (The International Speech Communication Association, 2011-08)
    Afrikaans is one of the eleven official languages of South Africa. It is classified as an under-resourced language. No annotated broadband speech corpora currently exist for Afrikaans. This article reports on the development ...
  • Raborife, M; Zerbian, S; Ewert, S (PRASA, 2011-11)
    The authors report on a study that involved the development of a corpus used to verify the performance of two tone labelling algorithms, with one algorithm being an improvement on the other. These algorithms were developed ...
  • Davel, M; Barnard, E (2006-09)
    Pronunciation lexicons often contain pronunciation variants. This can create two problems: It can be difficult to define these variants in an internally consistent way and it can also be difficult to extract generalised ...
  • Govender, Natasha; Barnard, E; Davel, M (PRASA, 2005-11)
    In order to bring the tools of statistical pattern recognition to bear on intonation modelling, we need tailor-made corpora in the languages of interest. We describe how two such corpora were developed (for isiZulu and ...
  • De Wet, Febe; Badenhorst, J; Modipa, T (Elsevier, 2016-05)
    The official languages of South Africa can still be classified as under-resourced with respect to the speech resources that are required for technology development. Harvesting speech data from existing sources is one means ...
  • Peché, M; Davel, MH; Barnard, E (South African Institute of Electrical Engineers (SAIEE), 2009-12)
    This article introduces the first Spoken Language Identification system developed to distinguish among all eleven of South Africa’s official languages. The PPR-LM (Parallel Phoneme Recognition followed by Language Modeling) ...
  • Zulu, N; Barnard, E (2006-11)
    This paper describes ongoing work in which the main objective is to quantitatively determine the linguistic distances between languages and dialects. The Levenshtein distance measure is applied to orthographic and phonetic ...
  • Ndwe, TJ; Sharma, Ameeth; Kgampe, M; Kuun, C (CSIR, 2008-11)
    Skilful dialogue design in an interactive voice response system has facilitated the effective use of a telephone-based health information syatem ny caregivers to HIV/AIDS-infected childern in Botswana. The intended users, ...
  • Van der Walt, W (CSIR Meraka, 2011-02)
    This document describes Open Source Software newly-developed under the NAP project. The software comprises a digital audio editor for the blind.
  • Schlunz, Georg I; Barnard, E (PRASA 2013 Proceedings, 2013-12)
    This paper introduces a model of affect to improve prosody in text-to-speech synthesis. It operates on the discourse level of text to predict the underlying linguistic factors that contribute towards emotional appraisal, ...
  • Molapo, R; Barnard, E; De Wet, Febe (PRASA 2013 Proceedings, 2013-12)
    The authors describe the integration of several tools to enable the end-to-end development of an Automatic Speech Recognition system in a typical under-resourced language. The authors analyse the data acquired by each of ...
  • Butgereit, LL (IST-Africa Conference, 2008-05)
    Mathematics education in South Africa needs help. This paper describes a project where school aged pupils could get help with their mathematics homework using MXit, South Africa's most popular instant messaging system, on ...
  • Joubert, G; Barnard, E (PRASA, 2005-11)
    The authors describe a system, based on open-source tools, that was developed in order to study the effect of network degenerations in Voice-over-Internet-Protocol applications on speech-recognition accuracy. Sophisticated ...
  • Mokgonyane, TB; Sefara, Tshephisho J; Manamela, MJ; Modipa, TI; Masekwameng, MS (IEEE, 2020-08)
    Automatic speaker recognition is the task of automatically determining or verifying the identity of a speaker from a recording of his or her speech sample and has been studied for many decades. One of the most important ...

Search ResearchSpace


Advanced Search

Browse

My Account