De Wet, F, A De Waal, and Gerhard B. Van Huyssteen. 2011. “Developing a broadband automatic speech recognition system for Afrikaans.” Proceedings of the 12th Annual Conference of the International Speech Communication Association (Interspeech 2011):3185-3188.
De Wet, De Waal & Van Huyssteen 2011
Abstract
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.
Written in:
English
Dealing with:
Afrikaans
Keywords
Afrikaans, under-resourced languages, automatic speech recognition, speech resources
Afrikaans keywords
Afrikaans, hulpbronskaars tale, outomatiese spraakherkenning, spraakhulpbronne