Peché, MDavel, MHBarnard, E2010-04-182010-04-182009-12Peché, M, Davel, MH and Barnard, E 2009. Development of a spoken language identification system for South African languages. South African Institute of Electrical Engineers (SAIEE), Africa Research Journal, Vol. 100(4), pp 97-1031991-1696http://www.saiee.org.za/publications/2009/Dec/100_4_2.pdfhttp://hdl.handle.net/10204/4043Copyright: 2009 South African Institute of Electrical EngineersThis article introduces the first Spoken Language Identification system developed to distinguish among all eleven of South Africa’s official languages. The PPR-LM (Parallel Phoneme Recognition followed by Language Modeling) architecture is implemented, and techniques such as phoneme frequency filtering, which aims to utilize the available training data to maximum efficiency, are utilized. The system performs reasonably well, achieving an overall accuracy of 71.72% on test samples of three to ten seconds in length. This accuracy improves when the predicted results are combined into language families, reaching an overall accuracy of 82.39%.enSpoken Language IdentificationS-LID systemParallel phoneme recognition followed by language modelingPPR-LMLanguage Identification systemSpoken Language developmentSouth African languagesArticlePeché, M., Davel, M., & Barnard, E. (2009). Development of a spoken language identification system for South African languages. http://hdl.handle.net/10204/4043Peché, M, MH Davel, and E Barnard "Development of a spoken language identification system for South African languages." (2009) http://hdl.handle.net/10204/4043Peché M, Davel M, Barnard E. Development of a spoken language identification system for South African languages. 2009; http://hdl.handle.net/10204/4043.TY - Article AU - Peché, M AU - Davel, MH AU - Barnard, E AB - This article introduces the first Spoken Language Identification system developed to distinguish among all eleven of South Africa’s official languages. The PPR-LM (Parallel Phoneme Recognition followed by Language Modeling) architecture is implemented, and techniques such as phoneme frequency filtering, which aims to utilize the available training data to maximum efficiency, are utilized. The system performs reasonably well, achieving an overall accuracy of 71.72% on test samples of three to ten seconds in length. This accuracy improves when the predicted results are combined into language families, reaching an overall accuracy of 82.39%. DA - 2009-12 DB - ResearchSpace DP - CSIR KW - Spoken Language Identification KW - S-LID system KW - Parallel phoneme recognition followed by language modeling KW - PPR-LM KW - Language Identification system KW - Spoken Language development KW - South African languages LK - https://researchspace.csir.co.za PY - 2009 SM - 1991-1696 T1 - Development of a spoken language identification system for South African languages TI - Development of a spoken language identification system for South African languages UR - http://hdl.handle.net/10204/4043 ER -