ResearchSpace

ASR performance analysis of an experimental call routing system

Show simple item record

dc.contributor.author Modipa, T
dc.contributor.author De Wet, Febe
dc.contributor.author Davel, M
dc.date.accessioned 2010-01-08T15:53:49Z
dc.date.available 2010-01-08T15:53:49Z
dc.date.issued 2009-11
dc.identifier.citation Modipa, P, De Wet, F and Davel, M. 2009. ASR performance analysis of an experimental call routing system. 20th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA). Stellenbosch, South Africa, 30 November - 01 December 2009, pp 127-130 en
dc.identifier.uri http://hdl.handle.net/10204/3860
dc.description 20th Annual Symposium of the Pattern Recognition Association of South Africa (PRASA). Stellenbosch, South Africa, 30 November - 01 December 2009 en
dc.description.abstract Call routing is an important application of Automatic Speech Recognition (ASR) technology. In this paper the authors discuss the main issues affecting the performance of a call routing system and describe the ASR component of the "AutoSecretary" system: an experimental call routing system performing automated secretarial functions. Specific attention is paid to the ASR pronunciation dictionary, and the impact of different dictionary configurations on recognition accuracy is investigated. While ASR accuracy, when evaluated off-line, is found to be high, accuracies recorded during on-line usage is much lower. Reasons for the lower than expected call completion rates are investigated through a detailed analysis of session log files, and improvements to the current system are proposed. en
dc.language.iso en en
dc.publisher PRASA 2009 en
dc.subject Call routing en
dc.subject Automated speech recognition en
dc.subject Proper name recognition en
dc.subject Spoken dialog systems en
dc.subject Call routing system en
dc.subject AutoSecretary system en
dc.subject PRASA 2009 en
dc.title ASR performance analysis of an experimental call routing system en
dc.type Conference Presentation en
dc.identifier.apacitation Modipa, T., De Wet, F., & Davel, M. (2009). ASR performance analysis of an experimental call routing system. PRASA 2009. http://hdl.handle.net/10204/3860 en_ZA
dc.identifier.chicagocitation Modipa, T, Febe De Wet, and M Davel. "ASR performance analysis of an experimental call routing system." (2009): http://hdl.handle.net/10204/3860 en_ZA
dc.identifier.vancouvercitation Modipa T, De Wet F, Davel M, ASR performance analysis of an experimental call routing system; PRASA 2009; 2009. http://hdl.handle.net/10204/3860 . en_ZA
dc.identifier.ris TY - Conference Presentation AU - Modipa, T AU - De Wet, Febe AU - Davel, M AB - Call routing is an important application of Automatic Speech Recognition (ASR) technology. In this paper the authors discuss the main issues affecting the performance of a call routing system and describe the ASR component of the "AutoSecretary" system: an experimental call routing system performing automated secretarial functions. Specific attention is paid to the ASR pronunciation dictionary, and the impact of different dictionary configurations on recognition accuracy is investigated. While ASR accuracy, when evaluated off-line, is found to be high, accuracies recorded during on-line usage is much lower. Reasons for the lower than expected call completion rates are investigated through a detailed analysis of session log files, and improvements to the current system are proposed. DA - 2009-11 DB - ResearchSpace DP - CSIR KW - Call routing KW - Automated speech recognition KW - Proper name recognition KW - Spoken dialog systems KW - Call routing system KW - AutoSecretary system KW - PRASA 2009 LK - https://researchspace.csir.co.za PY - 2009 T1 - ASR performance analysis of an experimental call routing system TI - ASR performance analysis of an experimental call routing system UR - http://hdl.handle.net/10204/3860 ER - en_ZA


Files in this item

Thumbnail
Name: Modipa_2009.pdf
Size: 2.140Mb
Format: PDF
View/Open

This item appears in the following Collection(s)

Show simple item record