DSpace
 

Researchspace >
General science, engineering & technology >
General science, engineering & technology >
General science, engineering & technology >

Please use this identifier to cite or link to this item: http://hdl.handle.net/10204/5501

Title: Default-and-refinement approach to pronunciation prediction
Authors: Davel, MH
Barnard, E
Keywords: Neural networks
Decision trees
Pronunciation
Analogy models
Instance based learning algorithms
Dynamically expanding context
PRASA 2004
Issue Date: Nov-2004
Publisher: PRASA 2004
Citation: Davel, MH and Barnard, E. 2004. Default-and-refinement approach to pronunciation prediction. 15th Annual Symposium of the Pattern Recognition Association of South Africa, Grabouw, South Africa, 25 to 26 November 2004
Abstract: The authors define a novel g-to-p prediction algorithm that utilises the concept of a 'default phoneme': a grapheme which is realised as a specific phoneme significantly more often than as any other phoneme. They found that this approach results in an algorithm that performs well across a range from very small to large data sets. The authors evaluated the algorithm on two benchmarked databases (Fonilex and NETtalk) and found highly competitive performance in asymptotic accuracy, initial learning speed, and model compactness.
Description: 15th Annual Symposium of the Pattern Recognition Association of South Africa, Grabouw, South Africa, 25 to 26 November 2004
URI: http://hdl.handle.net/10204/5501
Appears in Collections:Human language technologies
General science, engineering & technology

Files in This Item:

File Description SizeFormat
Davel_2004.pdf51.8 kBAdobe PDFView/Open
View Statistics

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

 

Valid XHTML 1.0! DSpace Software Copyright © 2002-2010  Duraspace - Feedback