ResearchSpace
→
Browsing by Impact Area

Browsing by Impact Area "Voice Computing"

Now showing items 1-13 of 13

Approximating a Zulu GF concrete syntax with a neural network for natural language understanding

Author: Marais, Laurette Date: Sep 2021 Multilingual 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
Bringing children’s dictionaries to digital life

Author: Wilken, Ilana ; Marais, Laurette Date: Nov 2023 South 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
Cognitive load of modern TTS systems under noisy conditions

Author: Govender, Avashna ; King, S Date: Nov 2023 Cognitive 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
Cross-lingual transfer using phonological features for resource-scarce text-to-speech

Author: Louw, Johannes A Date: Aug 2023 In 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
Descriptional complexity of non-unary self-verifying symmetric difference automata

Author: Marais, Laurette ; Van Zijl, L Date: May 2022 Unary 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
Extending the usage of adjectives in the Zulu AfWN

Author: Marais, Laurette ; Pretorius, L Date: Jan 2023 The 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
Gauging the accuracy of automatic speech data harvesting in five under-resourced languages

Author: Badenhorst, Jacob AC ; De Wet, F Date: Mar 2023 Recent 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
Investigating the feasibility of harvesting broadcast speech data to develop resources for South African languages

Author: Badenhorst, Jacob AC ; De Wet, Febe Date: Nov 2021 Sufficient 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
Mathematical content browsing for print-disabled readers based on virtual-world exploration and audio-visual sensory substitution

Author: Kruger, Rynhardt P ; De Wet, F ; Niesler, T Date: May 2023 Documents 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
Multi-MelGAN voice conversion for the creation of under-resourced child speech synthesis

Author: Govender, Avashna Date: May 2022 Voice 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
Multimodal, multilingual dynamic stories for literacy development and language learning

Author: Marais, Laurette ; Wilken, Ilana ; Pretorius, L ; Posthumus, L Date: Jul 2023 © 2023 Copyright held by the owner/author(s). Paper presented at the 5th International Conference on Conversational User Interfaces, Eindhoven, The Netherlands, 19-21 July 2023 Read more
NCHLT Auxiliary speech data for ASR technology development in South Africa

Author: Badenhorst, Jacob AC ; De Wet, Febe Date: Apr 2022 The 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
Parsing IsiZulu text using grammatical framework

Author: Marais, Laurette ; Pretorius, L Date: Jul 2023 While 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

Now showing items 1-13 of 13

Browse

All of ResearchSpace

Quick Links

Legislation and compliance

General Enquiries

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

Physical Address
Meiring Naudé Road
Brummeria
Pretoria
South Africa

Postal Address
PO Box 395
Pretoria 0001
South Africa

Social Connect

Resources on this site are free to download and reuse according to associated licensing provision. Please read the terms and conditions of usage of each resource.

Browsing by Impact Area "Voice Computing"

Browsing by Impact Area "Voice Computing"

Browse

All of ResearchSpace

Quick Links

Legislation and compliance

General Enquiries

Social Connect