Now showing items 1-11 of 11

    • Automatic alignment of audiobooks in Afrikaans 

      Van Heerden, Carel J.; De Wet, Febe; Davel, Marelie H. (Pattern recognition association of South Africa (PRASA), 2012)
      This paper reports on the automatic alignment of audiobooks in Afrikaans. An existing Afrikaans pronunciation dictionary and corpus of Afrikaans speech data are used to generate baseline acoustic models. The baseline system ...
    • Category-based phoneme-to-grapheme transliteration 

      Basson, Willem D.; Davel, Marelie H. (International Speech Communication Association ( ISCA ), 2013)
      Grapheme-based speech recognition systems are faster to develop but typically do not reach the same level of performance as phoneme-based systems. In this paper we introduce a technique for improving the performance of ...
    • Comparing grapheme-based and phoneme-based speech recognition for Afrikaans 

      Basson, Willem D.; Davel, Marelie H. (Pattern recognition association of South Africa (PRASA), 2012)
      This paper compares the recognition accuracy of a phoneme-based automatic speech recognition system with that of a grapheme-based system, using Afrikaans as case study. The first system is developed using a conventional ...
    • Context-dependent modelling of English vowels in Sepedi code-switched speech 

      Thipe I. Modipa; Febe de Wet; Davel, Marelie H. (Pattern recognition association of South Africa (PRASA), 2012)
      When modelling code-switched speech (utterances that contain a mixture of languages), the embedded language often contains phones not found in the matrix language. These are typically dealt with by either extending the ...
    • Implications of Sepedi/English code switching for ASR systems 

      Modipa, Thipe I.; De Wet, Febe; Davel, Marelie H. (Pattern recognition association of South Africa (PRASA), 2013)
      Code switching (the process of switching from one language to another during a conversation) is a common phenomenon in multilingual environments. Where a minority and dominant language coincide, code switching from the ...
    • Improved transition models for cepstral trajectories 

      Badenhorst, Jaco; Barnard, Etienne; Davel, Marelie H. (Pattern recognition association of South Africa (PRASA), 2012)
      We improve on a piece-wise linear model of the trajectories of Mel Frequency Cepstral Coefficients, which are commonly used as features in Automatic Speech Recognition. For this purpose, we have created a very clean ...
    • Medium-vocabulary speech recognition for under-resourced languages 

      Van Heerden, Charl J.; Barnard, Etienne; Davel, Marelie H. (SLTU, 2012)
      We report on the development of speech-recognition systems that are able to perform accurate recognition on mediumvocabulary tasks (i.e. tasks that require distinctions between approximately 200 different terms). We are ...
    • Multilingual pronunciations of proper names in a Southern African corpus 

      Jan W.F. Thirion; Etienne Barnard; Davel, Marelie H. (Pattern recognition association of South Africa (PRASA), 2012)
      We present our process for the development and analysis of a multilingual names corpus, called Multipron-split. It is derived from Multipron, a corpus collected in previous work [1], where names and speakers were drawn ...
    • N-gram based language identification of individual words 

      Giwa, Oluwapelumi; Davel, Marelie H. (PRASA, 2013)
      Various factors influence the accuracy with which the language of individual words can be classified using n-grams. We consider a South African text-based language identification (LID) task and experiment with two different ...
    • The semi-automated creation of stratified speech corpora 

      Van Heerden, Carel; Barnard, Etienne; Davel, Marelie H. (Pattern recognition association of South Africa (PRASA), 2013)
      Smartphones provide an efficient means for the collection of speech data; however, the quality of the corpora created in this fashion is not predictable. We describe an approach that allows us to post-process and rank ...
    • Validating smartphone-collected speech corpora 

      Van Heerden, Carel J.; Barnard, Etienne; Davel, Marelie H. (SLTU, 2012)
      We investigate the effectiveness with which the accuracy of a prompted speech corpus can be validated when minimal additional speech resources are available, and specifically when a language model in the target language ...