Search
Now showing items 1-10 of 32
Lwazi isiZulu TTS corpus
(Meraka Institute, CSIR, 2013-03-27) ~ - Resource Catalogue
Orthographic and phonemically aligned transcriptions
Phonetic aligner
(Meraka Institute, CSIR, 2013-07-01) ~ - Resource Index
Scripts for automatic phonetic alignment of speech corpora using hidden markov models (HMMs).
GNApp (VSep2009)
(Meraka Institute, CSIR, 2013-07-01) ~ - Resource Index
An augmentative and alternate communication (AAC) device which generates synthesised (or pre-recorded) speech as output based on icons. Available as a ...
Automated multilingual telephone access to financial services
(CatchWord, 2013-07-01) ~ - Resource Index
A working prototype automated telephone based enquiry and payment system functioning in three African languages, i.e. Zulu, Xhosa and Southern Sotho, ...
NCHLT-inlang Pronunciation Dictionaries
(Meraka Institute, CSIR; North-West University, 2014-07-04) ~ - Resource Catalogue
Broad phonemic transcriptions for 15,000 generic words in each of 11 languages. Each dictionary has an associated rule set for generating pronunciations ...
Lwazi III isiZulu TTS Corpus
(Meraka Institute, CSIR, 2016-06-17) ~ - Resource Catalogue
Complete audio recordings with orthographic transcriptions. TTS corpus for standard SA dialect. This corpus was created to enable the building of a TTS voice.
South African Multilingual Proper Names (Multipron) Corpus
(Molo Afrika Speech Technologies, 2013-10-03) ~ - Resource Catalogue
Audio, orthographic and auditory verified broad phonemic transcriptions of proper names in four languages, produced by speakers of the same four languages.
NoteTaker (vSep2009)
(Meraka Institute, CSIR, 2013-07-01) ~ - Resource Index
Replaces a number of dedicated devices for the blind. The Notetaker is really a communication and computing device for the blind and visually impaired ...
Corpus of multilingual code-switched soap opera speech
(Stellenbosch University, 2020-02-28)
The corpus comprises 26.9 hours of annotated multilingual speech that contains examples of code-switching in isiZulu, isiXhosa, Setswana, Sesotho and ...
NCHLT isiZulu Speech Corpus
(Meraka Institute, CSIR; North-West University, 2014-07-08) ~ - Resource Catalogue
Orthographically transcribed broadband speech corpus of approximately 56 hours, including a test suite of 8 speakers.