Zobrazeno 1 - 10
of 13
pro vyhledávání: '"Jaco Badenhorst"'
Autor:
Jaco Badenhorst, Febe de Wet
Publikováno v:
Data in Brief, Vol 41, Iss , Pp 107860- (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 describe
Externí odkaz:
https://doaj.org/article/5bd39d59bd4e40cfbbe2ec678ac06dd6
Autor:
Jaco Badenhorst, Febe de Wet
Publikováno v:
Information, Vol 10, Iss 9, p 268 (2019)
When the National Centre for Human Language Technology (NCHLT) Speech corpus was released, it created various opportunities for speech technology development in the 11 official, but critically under-resourced, languages of South Africa. Since then, t
Externí odkaz:
https://doaj.org/article/3e174d6abec84e9fa932b2da07107a07
Autor:
Jaco Badenhorst, Febe de Wet
Publikováno v:
Journal of the Digital Humanities Association of Southern Africa (DHASA).
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 are able t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4bd9dd451a7357d63ac109c4d50bcbd2
https://doi.org/10.55492/dhasa.v4i02.4031
https://doi.org/10.55492/dhasa.v4i02.4031
Autor:
Jaco Badenhorst, Febe de Wet
Publikováno v:
Data in Brief, Vol 41, Iss, Pp 107860-(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 describe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::98c893c40e6548bae3105b727feca94f
https://pubmed.ncbi.nlm.nih.gov/35141372
https://pubmed.ncbi.nlm.nih.gov/35141372
Autor:
Jaco Badenhorst, Febe de Wet
Publikováno v:
Journal of the Digital Humanities Association of Southern Africa (DHASA). 3
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 well-reso
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f41685edebbe6d1b552bef84665e265c
https://doi.org/10.55492/dhasa.v3i03.3820
https://doi.org/10.55492/dhasa.v3i03.3820
Autor:
Laurette Marais, Nina van Niekerk, Johannes A. Louw, Karen Calteaux, Ilana Wilken, Jaco Badenhorst, Glenn Stein
Publikováno v:
FUSION
The language contexts of multilingual developing countries such as South Africa are often characterised by communication challenges resulting from language differences. AwezaMed is a multilingual, multimodal speech-to-speech translation application f
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f3cdb6c6b9d7028be25f6e6b74c0064b
https://doi.org/10.23919/fusion45008.2020.9190240
https://doi.org/10.23919/fusion45008.2020.9190240
Publikováno v:
SLTU
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 to create additional resour
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::69cd9fd2fe9cce4f857b42153eb85e3d
Publikováno v:
SAICSIT
Speech-driven command and control is increasingly gaining momentum in the world around us. Using human speech to control appliances in trendy living spaces allows a user to control many appliances remotely. This paper discusses the rapid development
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c4f14b3e3f319cbe13b5c55adb74d6e9
https://doi.org/10.1145/3278681.3278704
https://doi.org/10.1145/3278681.3278704
Autor:
Jaco Badenhorst, Febe de Wet
Publikováno v:
2017 Pattern Recognition Association of South Africa and Robotics and Mechatronics (PRASA-RobMech).
This paper reports on the recognition of second language (L2) isiXhosa speech produced by beginner level adult language learners. The speech samples were produced and recorded during the development of a Mobile Assisted Language Learning (MALL) appli
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::da5f9e43eb3eed5848dca09c52c60592
https://doi.org/10.1109/robomech.2017.8261121
https://doi.org/10.1109/robomech.2017.8261121
Autor:
Febe de Wet, Willem Diederick Basson, Nic J. de Vries, Etienne Barnard, Alta de Waal, Marelie H. Davel, Jaco Badenhorst
Publikováno v:
Speech Communication. 56:119-131
Acoustic data collection for automatic speech recognition (ASR) purposes is a particularly challenging task when working with under-resourced languages, many of which are found in the developing world. We provide a brief overview of related data coll
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::5acbfbb362a8a9e3870aba60e25728a0
https://doi.org/10.1016/j.specom.2013.07.001
https://doi.org/10.1016/j.specom.2013.07.001