Davel, MHBarnard, E2012-01-182012-01-182004-10Davel, MH and Barnard, E. 2004. Efficient generation of pronunciation dictionaries: machine learning factors during bootstrapping. 8th International Conference on Spoken Language Processing, Jeju Island, Korea, 4 - 8 October 2004http://hdl.handle.net/10204/55028th International Conference on Spoken Language Processing, Jeju Island, Korea, 4 - 8 October 2004The authors focus on factors related to the underlying rule-extraction algorithms, and demonstrate variants of the Dynamically Expanding Context algorithm, which are beneficial for this application. They show that continuous updating of the learned rules, coupled with a new approach to grapheme-to-phoneme alignment and a sliding-window approach to choosing the content window, leads to an efficient and accurate bootstrapping mechanism. In this paper the authors describe the techniques implemented to optimise the process from a machine learning perspective and report on the results achieved.enAudio-enabled bootstrappingMachine learningHuman interventionSpoken language processingPronunciation dictionariesConference PresentationDavel, M., & Barnard, E. (2004). Efficient generation of pronunciation dictionaries: machine learning factors during bootstrapping. http://hdl.handle.net/10204/5502Davel, MH, and E Barnard. "Efficient generation of pronunciation dictionaries: machine learning factors during bootstrapping." (2004): http://hdl.handle.net/10204/5502Davel M, Barnard E, Efficient generation of pronunciation dictionaries: machine learning factors during bootstrapping; 2004. http://hdl.handle.net/10204/5502 .TY - Conference Presentation AU - Davel, MH AU - Barnard, E AB - The authors focus on factors related to the underlying rule-extraction algorithms, and demonstrate variants of the Dynamically Expanding Context algorithm, which are beneficial for this application. They show that continuous updating of the learned rules, coupled with a new approach to grapheme-to-phoneme alignment and a sliding-window approach to choosing the content window, leads to an efficient and accurate bootstrapping mechanism. In this paper the authors describe the techniques implemented to optimise the process from a machine learning perspective and report on the results achieved. DA - 2004-10 DB - ResearchSpace DP - CSIR KW - Audio-enabled bootstrapping KW - Machine learning KW - Human intervention KW - Spoken language processing KW - Pronunciation dictionaries LK - https://researchspace.csir.co.za PY - 2004 T1 - Efficient generation of pronunciation dictionaries: machine learning factors during bootstrapping TI - Efficient generation of pronunciation dictionaries: machine learning factors during bootstrapping UR - http://hdl.handle.net/10204/5502 ER -