dc.contributor.author |
Kleynhans, N
|
|
dc.contributor.author |
Molapo, R
|
|
dc.contributor.author |
De Wet, Febe
|
|
dc.date.accessioned |
2013-01-28T07:56:22Z |
|
dc.date.available |
2013-01-28T07:56:22Z |
|
dc.date.issued |
2012-11 |
|
dc.identifier.citation |
Kleynhans, N, Molapo, R and De Wet, F. 2012. Acoustic model optimisation for a call routing system. PRASA 2012, CSIR International Convention Centre, Pretoria, 29-30 November 2012 |
en_US |
dc.identifier.issn |
10116 |
|
dc.identifier.uri |
http://www.prasa.org/proceedings/2012/prasa2012-32.pdf
|
|
dc.identifier.uri |
http://hdl.handle.net/10204/6434
|
|
dc.description |
PRASA 2012, CSIR International Convention Centre, Pretoria, 29-30 November 2012 |
en_US |
dc.description.abstract |
The paper presents work aimed at optimising acoustic models for the AutoSecretary call routing system. To develop the optimised acoustic models: (1) an appropriate phone set was selected and used to create a pronunciation dictionary, (2) various cepstral normalization techniques were investigated, (3) three South African corpora and multiple training data combinations were used to train the acoustic models, and, (4) model-space transformations were applied. Using an independent testing corpus, which contained proper names and South African language names, a named-language recognition accuracy of 95.11 % and proper name recognition accuracy of 93.31% were obtained. |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
PRASA |
en_US |
dc.relation.ispartofseries |
Workflow; |
|
dc.subject |
AutoSecretary call routing system |
en_US |
dc.subject |
Call routing systems |
en_US |
dc.subject |
Acoustic models |
en_US |
dc.title |
Acoustic model optimisation for a call routing system |
en_US |
dc.type |
Conference Presentation |
en_US |