INTERSPEECH 2011
12th Annual Conference of the International Speech Communication Association

Florence, Italy
August 27-31. 2011

Developing a Broadband Automatic Speech Recognition System for Afrikaans

Febe de Wet (1), Alta de Waal (1), Gerhard B. van Huyssteen (2)

(1) CSIR, South Africa
(2) North-West University, South Africa

Afrikaans is one of the eleven official languages of South Africa. It is classified as an under-resourced language. No annotated broadband speech corpora currently exist for Afrikaans. This article reports on the development of speech resources for Afrikaans, specifically a broadband speech corpus and an extended pronunciation dictionary. Baseline results for an ASR system that was built using these resources are also presented. In addition, the article suggests different strategies to exploit the close relationship between Afrikaans and Dutch for the purposes of technology development.

Full Paper

Bibliographic reference.  Wet, Febe de / Waal, Alta de / Huyssteen, Gerhard B. van (2011): "Developing a broadband automatic speech recognition system for Afrikaans", In INTERSPEECH-2011, 3185-3188.