Welcome to the South African Centre for Digital Language Resources website
Log In

Log In

Forgot Your Password?

Tray Subtotal: R0.00

Resource Index

In 2009, the South African National HLT Network (NHN) funded a technology audit that was conducted to form a clear profile of the research and development activiites in the human language technology field in South Africa. This audit was used as the basis for the RMA Index, which is a list of South African resources with the relevant metadata (information such as developer details and specifications). Some of these resources are included in the RMA Catalogue, and are therefore available for download.

Items 1 to 50 of 109 total

per page
Page:
  1. 1
  2. 2
  3. 3

Set Descending Direction
Switch View
  • (SRP-Type A Research) Ability-based technology interventions
    Not Available

    (SRP-Type A Research) Ability-based technology interventions

    R0.00

    Research conducted to investigate how the use of multiple modalities can improve training for persons based on their abilities, language, literacy. One possible output modality to be used is speech synthesis (if the person does not have the ability to see), whilst speech recognition as input modality can be used for a person that has the ability to talk and not the ability to physically interact with the PC. (A technology demonstrator is currently available in English & South African Sign Language)

    Learn More |
  • Afrikaans 20,000 Word Rule Set (v.2007)
    Not Available

    Afrikaans 20,000 Word Rule Set (v.2007)

    R0.00

    Grapheme-to-phoneme rule set based on 20,000-word Afrikaans pronunciation dictionary

    Learn More |
  • Afrikaans Chunker
    Not Available

    Afrikaans Chunker

    R0.00

    Chunker for Afrikaans based on memory-based machine learning.

    Learn More |
  • Afrikaans Part of Speech Data
    Not Available

    Afrikaans Part of Speech Data

    R0.00

    POS annotated data used to train POS tagger. The tagset was specifically designed for Afrikaans and consists of 139 pos-tags.

    Learn More |
  • Afrikaans Pronunciation Dictionary
    Not Available

    Afrikaans Pronunciation Dictionary

    R0.00

    Pronunciation dictionary compiled from Lwazi ASR dictionary and the "Taalkommissie Korpus". Dictionary to be used for the development of a large vocabulary continuous speech recognition system for Afrikaans.

    Learn More |
  • Afrikaans Radio News Speech Corpus
    Not Available

    Afrikaans Radio News Speech Corpus

    R0.00

    News bulletins purchased from the SABC. Data to be used for the development of a large vocabulary continuous speech recognition system for Afrikaans.

    Learn More |
  • Afrikaans TnT-Tagger
    Not Available

    Afrikaans TnT-Tagger

    R0.00

    The Afrikaans TnT-tagger is a part of speech tagger that can be used to add part of speech tags to Afrikaans texts.

    Learn More |
  • Afrikaans Trajectories
    Not Available

    Afrikaans Trajectories

    R0.00

    Frequency analysis of Afrikaans words in the Media24 Archive from 1980-2003 presented in the form of total frequency per word in 5 year intervals as well as frequency per word expressed per 50 million tokens. Pop-up graph for visual display.

    Learn More |
  • Afrikaans Wordnet 1.0
    Not Available

    Afrikaans Wordnet 1.0

    R0.00

    The Afrikaans WordNet is a lexical reference source displaying some similarities with dictionaries and thesauri. Together with ALEXANDER, our other Afrikaans database, it should be of great use as a reference source and application.

    Learn More |
  • Afrikaans-English-Xhosa-Zulu Aid on Cellphone
    Not Available

    Afrikaans-English-Xhosa-Zulu Aid on Cellphone

    R0.00

    Translations for words in 4 languages

    Learn More |
  • Afrikaanse Speltoetser 3.1
    Not Available

    Afrikaanse Speltoetser 3.1

    R0.00

    Afrikaans spelling checker that is compatible with Microsoft Office 2000 and up. This version of CTexT's well-known spelling checker for Afrikaans now recognises more than 430 000 words, which includes a wide variety of pronouns, technical terms and acronyms. Thanks to advanced morphological analysis, Afrikaanse Speltoetser 3.1 also recognises a large number of compounds and inflections.

    Learn More |
  • AST Prototype Demonstrators
    Not Available

    AST Prototype Demonstrators

    R0.00

    South African English prototype of an automated hotel information and reservation system developed during the AST project. The prototype system was subjected to usability tests.

    Learn More |
  • AST Speech Generation Package
    Not Available

    AST Speech Generation Package

    R0.00

    Limited domain speech synthesis system developed during the AST project. (unit selection)

    Learn More |
  • Asterisk Nuance 1.4.
    Not Available

    Asterisk Nuance 1.4.

    R0.00

    Integration of commercial Nuance speech-recognition engine to the Asterisk open-source platform.

    Learn More |
  • AStudio
    Not Available

    AStudio

    R0.00

    This software incorporates a graphic interface that allows for the development of a flowchart representation of the state machine that will form the speech application.

    Learn More |
  • Automated multilingual telephone access to financial services
    Not Available

    Automated multilingual telephone access to financial services

    R0.00

    A working prototype automated telephone based enquiry and payment system functioning in three African languages, i.e. Zulu, Xhosa and Southern Sotho, in a financially related application, making provision for code-mixing between these languages and English.

    Learn More |
  • Automatic Oral Proficiency Assessment Tool
    Not Available

    Automatic Oral Proficiency Assessment Tool

    R0.00

    Tools developed as part of the "Development of Resources for Intelligent Computer-Assisted Language Learning" project sponsored by the NHN.

    Learn More |
  • Boomerang v1.0
    Not Available

    Boomerang v1.0

    R0.00

    Performs outbound call campaigns and executes Javascript-scripted IVR callflows especially for marketing companies companies with extensive client interaction (e.g. banking, insurance).

    Learn More |
  • Calomo
    Not Available

    Calomo

    R0.00

    Calomo is a hyphenator for Afrikaans, which can be implemented in any NLP system.

    Learn More |
  • CKarma
    Not Available

    CKarma

    R0.00

    CKarma is a compound analyser for Afrikaans, to be used for the detection of word boundaries within compounds.

    Learn More |
  • Combination Tagger
    Not Available

    Combination Tagger

    R0.00

    The combination tagger framework uses MBT, SVM, MXPOST and TnT. Each tagger receives a weight by which it can vote for a tag.

    Learn More |
  • CompanyCall v1.0
    Not Available

    CompanyCall v1.0

    R0.00

    Routes calls based on spoken company name, south african names, ses ASR name re ??, which domain) directory assistance, 08606companycall.co.za.

    Learn More |
  • CorpusCatcher
    Not Available

    CorpusCatcher

    R0.00

    Corpus Catcher is a tool that is designed to crawl the web to retrieve data for inclusion in a corpus. It makes use of seed documents/wordlists to construct queries to retrieve documents

    Learn More |
  • CTexT Afrikaanse Grammatikatoetser 1.0
    Not Available

    CTexT Afrikaanse Grammatikatoetser 1.0

    R0.00

    The CTexT Afrikaanse Grammatikatoetser is the first Afrikaans grammar checker for Microsoft Office, and can identify a number of grammatical and style errors.

    Learn More |
  • CTexT Afrikaanse Tesourus 1.0
    Not Available

    CTexT Afrikaanse Tesourus 1.0

    R0.00

    The CTexT® Afrikaanse Thesaurus is based on the Groot Afrikaans Tesourus of De Stadler.

    Learn More |
  • CTexT Multilingual Text Corpora
    Not Available

    CTexT Multilingual Text Corpora

    R0.00

    Document level aligned corpora for machine translation purposes.

    Learn More |
  • Dagsê 1.1; Ngenani 3.1; Sondelani1.1; Tsenang3.1
    Not Available

    Dagsê 1.1; Ngenani 3.1; Sondelani1.1; Tsenang3.1

    R0.00

    An individual's endeavour to speak to someone in their mother tongue cultivates respect. This in turn may lead to better understanding between culture groups. CTexT and partners can help with our language learning software

    Learn More |
  • Domain Independent TTS for isiZulu
    Not Available

    Domain Independent TTS for isiZulu

    R0.00

    isiZulu TTS system developed during a bilateral research project (South Africa/Japan). HTS based (HMM-based synthesis)

    Learn More |
  • DSAE Citations Database
    Not Available

    DSAE Citations Database

    R0.00

    Citations contained in A Dictionary of South African English on Historical Principles (1996) covering English usage in SA up to 1995, plus new material under development

    Learn More |
  • EtsaTrans
    Not Available

    EtsaTrans

    R0.00

    The EtsaTrans machine translation system was build with the intention to do translation of documents from a source language to a target language. Currently the user interface is available in English, Afrikaans, Sesotho and IsiXhosa.

    Learn More |
  • EWA
    Not Available

    EWA

    R0.00

    Die Etimologiewoordeboek van die Afrikaanse Taal is an Afrikaans etymological dictionary, distributed in Folio Views for Windows 4.6.0.7

    Learn More |
  • Fannie Sebolela Oral Corpus
    Not Available

    Fannie Sebolela Oral Corpus

    R0.00

    Tape recordings and transcriptions of 13 mother tongue speakers. Transcribed orthographically.

    Learn More |
  • Format Normaliser 1.0.
    Not Available

    Format Normaliser 1.0.

    R0.00

    Normalises input files to txt, utf8, replaces smart quotes with straight quotes, removes empty lines, etc.

    Learn More |
  • GNApp (VSep2009)
    Not Available

    GNApp (VSep2009)

    R0.00

    An augmentative and alternate communication (AAC) device which generates synthesised (or pre-recorded) speech as output based on icons. Available as a demonstration. (Uses eSpeak, flite, festival, freetts for synthesis. Supports any language that the TTS engine supports. Demonstrations available for Eng, Afr, isizulu

    Learn More |
  • Habakuk
    Not Available

    Habakuk

    R0.00

    Habakuk is a rule-based hyphenator for Afrikaans, which can be implemented in any NLP system.

    Learn More |
  • Homophone Disambiguatior 1.0.
    Not Available

    Homophone Disambiguatior 1.0.

    R0.00

    Developed to disambiguate Afrikaans homophones.

    Learn More |
  • Hyphenator 1.0.
    Not Available

    Hyphenator 1.0.

    R0.00

    Rule-based hyphenator which can be implemented in any NLP system. It takes as input a string, and produces as output an analysed string, without any tags. For example, the string "hondehokdak" ('dog house roof') will be analysed as "hon-de-hok-dak", where the hyphen indicates syllable boundaries on an orthographic level. Rules implemented in Perl.

    Learn More |
  • Intonation 2005 Corpus
    Not Available

    Intonation 2005 Corpus

    R0.00

    Read speech, 2 speakers in each of isiZulu, isiXhosa

    Learn More |
  • Intonation model for Bantu tone languages
    Not Available

    Intonation model for Bantu tone languages

    R0.00

    Theoretical linguistic intonation model for Setswana-Sesotho and isiZulu, formulated as ste-wise rules in prose.

    Learn More |
  • isiNdebele Spelling Checker 1.0
    Not Available

    isiNdebele Spelling Checker 1.0

    R0.00

    Spelling checkers and hyphenators for South African languages compatible with Microsoft® Office 2000, XP, 2003, 2007, 2010 or Microsoft® Office 2013. Extended research by CTexT ensures that spell checking and hyphenation occur effortlessly within the parameters of the standard written variant of each language. It also includes a comprehensive word list and hyphenation.

    Learn More |
  • isiXhosa Spelling Checker 1.1
    Not Available

    isiXhosa Spelling Checker 1.1

    R0.00

    Spelling checkers and hyphenators for South African languages compatible with Microsoft® Office 2000, XP, 2003, 2007, 2010 or Microsoft® Office 2013. Extended research by CTexT ensures that spell checking and hyphenation occur effortlessly within the parameters of the standard written variant of each language. It also includes a comprehensive word list and hyphenation.

    Learn More |
  • isiZulu Spelling Checker 1.1
    Not Available

    isiZulu Spelling Checker 1.1

    R0.00

    Spelling checkers and hyphenators for South African languages compatible with Microsoft® Office 2000, XP, 2003, 2007, 2010 or Microsoft® Office 2013. Extended research by CTexT ensures that spell checking and hyphenation occur effortlessly within the parameters of the standard written variant of each language. It also includes a comprehensive word list and hyphenation.

    Learn More |
  • KALAS
    Not Available

    KALAS

    R0.00

    KALAS is a rule-based compound analyser for Afrikaans, to be used for the detection of word boundaries within compounds.

    Learn More |
  • Lexi
    Not Available

    Lexi

    R0.00

    Citation database that replaces and supplements old index cards. Contains citations and source reference. Citations used in WAT as necessary.

    Learn More |
  • Little Dictionary on Cellphone
    Not Available

    Little Dictionary on Cellphone

    R0.00

    Afrikaans-English dictionary with 30 000 lemmas suitable for general market

    Learn More |
  • Media24 Afrikaans Test Corpus
    Not Available

    Media24 Afrikaans Test Corpus

    R0.00

    Collection of texts from Media24 newspaper texts for building lexicographic modules such as the Afrikaans Trajectories

    Learn More |
  • MELFA (Mobile E-Learning for Africa)
    Not Available

    MELFA (Mobile E-Learning for Africa)

    R0.00

    Embedded TTS on mobile phones providing speech output of full texts for various types of applications.

    Learn More |
  • Morphosyntactic Drag-and-Drop Tagger for isiXhosa
    Not Available

    Morphosyntactic Drag-and-Drop Tagger for isiXhosa

    R0.00

    The tagger and the tag set were developed under the auspices of the Spoken Language Corpus Project (Unisa & Gothenburg University) as part of the annotations tools for transcriptions.

    Learn More |
  • Morphosyntactic Tag Set for isiXhosa
    Not Available

    Morphosyntactic Tag Set for isiXhosa

    R0.00

    The tagger and the tag set were developed under the auspices of the Spoken Language Corpus Project (Unisa & Gothenburg University) as part of the annotations tools for transcriptions.

    Learn More |
  • Multilingual Arts & Culture Intermediate Phase Terminology List
    Not Available

    Multilingual Arts & Culture Intermediate Phase Terminology List

    R0.00

    550 English source terms with their equivalents in the ten other official South African languages. The list was compiled in collaboration with subject field specialists. Terms were excerpted from arts and culture learner books, teacher’s guides and manuals, arts and culture journals and magazines, etc. Please contact the National Language Service for usage conditions.

    Learn More |

Items 1 to 50 of 109 total

per page
Page:
  1. 1
  2. 2
  3. 3

Set Descending Direction
Switch View