Barnard, EDavel, MVan Heerden, C2012-02-152012-02-152009-09Barnard, E, Davel, M and Van Heerden, C. ASR corpus design for resource-scarce languages. 10th Annual Conference of the International Speech Communication Association (Interspeech 2009), Brighton, UK, 6-10 September 2009, pp 2847-2850http://hdl.handle.net/10204/557610th Annual Conference of the International Speech Communication Association (Interspeech 2009), Brighton, UK, 6-10 September 2009The authors investigate the number of speakers and the amount of data that is required for the development of useable speaker-independent speech-recognition systems in resource-scarce languages. Their experiments employ the Lwazi corpus, which contains speech in the eleven official languages of South Africa. They find that a surprisingly small number of speakers (fewer than 50) and around 10 to 20 hours of speech per language are sufficient for the purposes of acceptable phone-based recognition.enAccurate speech recognition (ASR)LwaziResource scarce languagesCorpus designConference PresentationBarnard, E., Davel, M., & Van Heerden, C. (2009). ASR corpus design for resource-scarce languages. ISCA. http://hdl.handle.net/10204/5576Barnard, E, M Davel, and C Van Heerden. "ASR corpus design for resource-scarce languages." (2009): http://hdl.handle.net/10204/5576Barnard E, Davel M, Van Heerden C, ASR corpus design for resource-scarce languages; ISCA; 2009. http://hdl.handle.net/10204/5576 .TY - Conference Presentation AU - Barnard, E AU - Davel, M AU - Van Heerden, C AB - The authors investigate the number of speakers and the amount of data that is required for the development of useable speaker-independent speech-recognition systems in resource-scarce languages. Their experiments employ the Lwazi corpus, which contains speech in the eleven official languages of South Africa. They find that a surprisingly small number of speakers (fewer than 50) and around 10 to 20 hours of speech per language are sufficient for the purposes of acceptable phone-based recognition. DA - 2009-09 DB - ResearchSpace DP - CSIR KW - Accurate speech recognition (ASR) KW - Lwazi KW - Resource scarce languages KW - Corpus design LK - https://researchspace.csir.co.za PY - 2009 T1 - ASR corpus design for resource-scarce languages TI - ASR corpus design for resource-scarce languages UR - http://hdl.handle.net/10204/5576 ER -