De Wet, FebeDe Waal, AVan Huyssteen, GB2012-01-122012-01-122011-08De Wet, F, De Waal, A and Van Huyssteen, GB. 2011. Developing a broadband automatic speech recognition system for Afrikaans. 12 Annual Conference of the International Speech Communication Association (Interspeech 2011), Florence, Italy, 27-31 August 2011http://hdl.handle.net/10204/547812 Annual Conference of the International Speech Communication Association (Interspeech 2011), Florence, Italy, 27-31 August 2011Afrikaans 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.enAfrikaans speech recognitionAfrikaans speech resourcesUnder resourced languagesAfrikaansAutomatic speech recognitionSpeech resourcesInterspeech 2011Speech communicationConference PresentationDe Wet, F., De Waal, A., & Van Huyssteen, G. (2011). Developing a broadband automatic speech recognition system for Afrikaans. The International Speech Communication Association. http://hdl.handle.net/10204/5478De Wet, Febe, A De Waal, and GB Van Huyssteen. "Developing a broadband automatic speech recognition system for Afrikaans." (2011): http://hdl.handle.net/10204/5478De Wet F, De Waal A, Van Huyssteen G, Developing a broadband automatic speech recognition system for Afrikaans; The International Speech Communication Association; 2011. http://hdl.handle.net/10204/5478 .TY - Conference Presentation AU - De Wet, Febe AU - De Waal, A AU - Van Huyssteen, GB AB - 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. DA - 2011-08 DB - ResearchSpace DP - CSIR KW - Afrikaans speech recognition KW - Afrikaans speech resources KW - Under resourced languages KW - Afrikaans KW - Automatic speech recognition KW - Speech resources KW - Interspeech 2011 KW - Speech communication LK - https://researchspace.csir.co.za PY - 2011 T1 - Developing a broadband automatic speech recognition system for Afrikaans TI - Developing a broadband automatic speech recognition system for Afrikaans UR - http://hdl.handle.net/10204/5478 ER -