Code-switched English pronunciation modeling for Swahili spoken term detection
| dc.contributor.author | Kleynhans, Neil | |
| dc.contributor.author | Hartman, William | |
| dc.contributor.author | Van Niekerk, Daniel | |
| dc.contributor.author | Van Heerden, Charl | |
| dc.contributor.author | Schwartz, Rich | |
| dc.contributor.author | Tsakalidis, Stavros | |
| dc.contributor.author | Davel, Marelie H. | |
| dc.contributor.researchID | 23607955 - Davel, Marelie Hattingh | |
| dc.contributor.researchID | 21022658 - Van Niekerk, Daniël Rudolph | |
| dc.date.accessioned | 2019-02-07T09:45:53Z | |
| dc.date.available | 2019-02-07T09:45:53Z | |
| dc.date.issued | 2016-05 | |
| dc.description.abstract | We investigate modeling strategies for English code-switched words as found in a Swahili spoken term detection system. Code switching, where speakers switch language in a conversation, occurs frequently in multilingual environments, and typically deteriorates STD performance. Analysis is performed in the context of the IARPA Babel program which focuses on rapid STD system development for under-resourced languages. Our results show that approaches that specifically target the modeling of code-switched words, significantly improve the detection performance of these words. | en_US |
| dc.identifier.citation | Neil Kleynhans, William Hartman, Daniel van Niekerk, Charl van Heerden, Rich Schwartz, Stavros Tsakalidis and Marelie Davel, “Code-switched English pronunciation modeling for Swahili spoken term detection”, Procedia Computer Science: Spoken Language Technology for Under-resourced Languages, pp 128-135, Yogyakarta, Indonesia, May 2016. | en_US |
| dc.identifier.uri | http://hdl.handle.net/10394/31798 | |
| dc.identifier.uri | https://researchspace.csir.co.za/dspace/handle/10204/8916 | |
| dc.identifier.uri | https://www.researchgate.net/publication/301827889_Code-switched_English_Pronunciation_Modeling_for_Swahili_Spoken_Term_Detection | |
| dc.language.iso | en | en_US |
| dc.publisher | Procedia Computer Science: Spoken Language Technology for Under-resourced Languages | en_US |
| dc.subject | Spoken term detection | en_US |
| dc.subject | code switching | en_US |
| dc.subject | Swahili | en_US |
| dc.subject | pronunciation modeling | en_US |
| dc.title | Code-switched English pronunciation modeling for Swahili spoken term detection | en_US |
| dc.type | Article | en_US |