SADiLaR Language Resource Repository
Not a member yet
536 research outputs found
Sort by
Pharos Speltoetser en Woordafbreker
Corrects typing and spelling errors and hyphenate words correctl
Openphone Health Helpline (vApr 2008)
A telephone-based IVR service (DTMF access) for providing health-related information on various topics such as medication, nutrition, hygiene, common ailments, and FAQs, to caregivers of HIV positive children in Botswana in the local langauge Setswana
Phonetic aligner
Scripts for automatic phonetic alignment of speech corpora using hidden markov models (HMMs)
TurboAnnotate1.0
TurboAnnotate is a user-friendly annotating environment (i.e. tool) for bootstrapping linguistic data for machine-learning purposes, or for manually creating gold standards or other annotated lists. This first version of TurboAnnotate was developed with the specific the task of hyphenation for South African languages in mind. In the annotation GUI, the annotator simply drags the mouse over the part of the word to be annotated, and on release of the mouse button, the selection changes colour. The machine learning system that we use in our system is the well-known Tilburg Memory-Based Learner (TiMBL; Daelemans et al, 2004). Van Huyssteen & Puttkammer (2007) reports that TurboAnnotate could not only ensure higher accuracy in human annotations, but could also save on human effort required (at least in the case of Afrikaans). Work on TurboAnnotate continues
Lwazi Siswati Pronunciation Dictionary
General phonemic pronunciations for frequently occurring words in SA languages. Dictionaries were developed to be practically usable for speech technology systems, rather than phonetically accurate. Audio samples of all phonemes included. A letter-to-sound rule set for predicting the pronunciations of generic words included. (Separate entry describes rule sets.
Sepedi Custom Dictionary for Government Domain
Word list developed as a custom dictionary for use in the spelling checkers as part of the spelling checker project for the Department of Arts and Culture. Contains words exclusive to the government domain or words that are not part of the official orthography of the language