ResearchSpace

Verifying pronunciation dictionaries using conflict analysis

Show simple item record

dc.contributor.author Davel, MH
dc.contributor.author De Wet, Febe
dc.date.accessioned 2010-12-21T08:36:13Z
dc.date.available 2010-12-21T08:36:13Z
dc.date.issued 2010-09
dc.identifier.citation Davel, MH and De Wet, F. 2010. Verifying pronunciation dictionaries using conflict analysis. Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010), Makuhari, Japan, 26-30 September 2010, pp 1898-1901 en
dc.identifier.uri http://hdl.handle.net/10204/4693
dc.description Proceedings of the 11th Annual Conference of the International Speech Communication Association (INTERSPEECH 2010), Makuhari, Japan, 26-30 September 2010 en
dc.description.abstract The authors describe a new language-independent technique for automatically identifying errors in an electronic pronunciation dictionary by analyzing the source of conflicting patterns directly.They evaluate the effectiveness of the technique in two ways: they perform a controlled experiment using artificially corrupted data (allowing us to measure precision and recall exactly); and then apply the technique to a real-world pronunciation dictionary, demonstrating its effectiveness in practice. They also introduce a new freely available pronunciation resource (the RCRL Afrikaans Pronunciation Dictionary), the largest such dictionary that currently exists. en
dc.language.iso en en
dc.relation.ispartofseries Conference Paper en
dc.subject Pronunciation dictionaries en
dc.subject Error detection en
dc.subject Quality verification en
dc.subject Grapheme-to-phonem en
dc.subject Speech communication en
dc.subject Interspeech 2010 en
dc.title Verifying pronunciation dictionaries using conflict analysis en
dc.type Conference Presentation en
dc.identifier.apacitation Davel, M., & De Wet, F. (2010). Verifying pronunciation dictionaries using conflict analysis. http://hdl.handle.net/10204/4693 en_ZA
dc.identifier.chicagocitation Davel, MH, and Febe De Wet. "Verifying pronunciation dictionaries using conflict analysis." (2010): http://hdl.handle.net/10204/4693 en_ZA
dc.identifier.vancouvercitation Davel M, De Wet F, Verifying pronunciation dictionaries using conflict analysis; 2010. http://hdl.handle.net/10204/4693 . en_ZA
dc.identifier.ris TY - Conference Presentation AU - Davel, MH AU - De Wet, Febe AB - The authors describe a new language-independent technique for automatically identifying errors in an electronic pronunciation dictionary by analyzing the source of conflicting patterns directly.They evaluate the effectiveness of the technique in two ways: they perform a controlled experiment using artificially corrupted data (allowing us to measure precision and recall exactly); and then apply the technique to a real-world pronunciation dictionary, demonstrating its effectiveness in practice. They also introduce a new freely available pronunciation resource (the RCRL Afrikaans Pronunciation Dictionary), the largest such dictionary that currently exists. DA - 2010-09 DB - ResearchSpace DP - CSIR KW - Pronunciation dictionaries KW - Error detection KW - Quality verification KW - Grapheme-to-phonem KW - Speech communication KW - Interspeech 2010 LK - https://researchspace.csir.co.za PY - 2010 T1 - Verifying pronunciation dictionaries using conflict analysis TI - Verifying pronunciation dictionaries using conflict analysis UR - http://hdl.handle.net/10204/4693 ER - en_ZA


Files in this item

Thumbnail
Name: Davel_2010.pdf
Size: 114.4Kb
Format: PDF
View/Open

This item appears in the following Collection(s)

Show simple item record