Author:Marais, LauretteDate:Sep 2021Multilingual Grammatical Framework (GF) domain grammars have been used in a variety of different applications, including question answering, where concrete syntaxes for parsing questions and generating answers are typically required for each ...Read more
Author:Wilken, Ilana; Marais, LauretteDate:Nov 2023South Africa is facing a literacy crisis, with the latest PIRLS results showing that 8 out of 10 learners cannot read for basic comprehension by the time they leave the foundation phase. In this climate, the development of strategies to assist ...Read more
Author:Govender, Avashna; King, SDate:Nov 2023Cognitive load of text-to-speech (TTS) synthesis systems measured in the past consistently showed that processing synthetic speech is more difficult to process than human speech in the presence of noise. However, the systems previously evaluated ...Read more
Author:Louw, Johannes ADate:Aug 2023In this work, we explore the use of phonological features incross-lingual transfer within resource-scarce settings. We modify the architecture of VITS to accept a phonological feature vector as input, instead of phonemes or characters. ...Read more
Author:Marais, Laurette; Van Zijl, LDate:May 2022Unary self-verifying symmetric difference automata have a known tight bound of 2n-1-1 for their state complexity. We now consider the non-unary case and show that, for every n=2, there is a regular language Ln accepted by a non-unary ...Read more
Author:Marais, Laurette; Pretorius, LDate:Jan 2023The African languages Wordnet (AfWN) for Zulu (ZWN) was built using the expand approach, which relies on the translation of concepts in the Princeton WordNet (PWN), while retaining their PWN lexical categories. In this paper the focus is on ...Read more
Author:Badenhorst, Jacob AC; De Wet, FDate:Mar 2023Recent research on deep-learning architectures has resulted in substantial improvements in automatic speech recognition accuracy. The leaps of progress made in well-resourced languages can be attributed to the fact that these architectures ...Read more
Author:Badenhorst, Jacob AC; De Wet, FebeDate:Nov 2021Sufficient target language data remains an important factor in the development of automatic speech recognition (ASR) systems. For instance, the substantial improvement in acoustic modelling that deep architectures have recently achieved for ...Read more
Author:Kruger, Rynhardt P; De Wet, F; Niesler, TDate:May 2023Documents containing mathematical content remain largely inaccessible to blind and visually impaired readers because they are predominantly published as untagged PDF which does not include the semantic data necessary for effective accessibility. ...Read more
Author:Govender, AvashnaDate:May 2022Voice conversion (VC) is an important technique for the development of text-to-speech voices in the use case of lacking speech resources. VC can convert an audio signal from a source speaker to a specific target speaker whilst maintaining the ...Read more
Author:Badenhorst, Jacob AC; De Wet, FebeDate:Apr 2022The aim of the National Centre for Human Language Technology (NCHLT) project was to create speech and text resources that would enable Human Language Technology (HLT) development for the 11 official languages of South Africa. The speech data ...Read more
Author:Marais, Laurette; Pretorius, LDate:Jul 2023While Grammatical Framework (GF) resource grammars are primarily intended as linguistic software libraries, they can also be employed to enable syntax parsing via the GF runtime system. The isiZulu resource grammar (ZRG) in conjunction with ...Read more