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/10204/5631

Title: Acoustic modelling of Sepedi affricates for ASR
Authors: Modipa, T
Davel, M
De Wet, F
Keywords: Artificial intelligence
Natural language processing
Speech recognition and synthesis
Sepedi
Acoustic models
Phonemes
Affricates
Issue Date: Oct-2010
Publisher: ACM Digital Library
Citation: Modipa, T, Davel, M and De Wet, F. Acoustic modelling of Sepedi affricates for ASR. 2010 Annual Research Conference of the South African Institute for Computer Scientists and Information Technologists (SAICSIT 2010), Bela Bela, South Africa, 11-13 October 2010
Series/Report no.: Workflow;5161
Abstract: Automatic speech recognition (ASR) systems are increasingly being developed for under-resourced languages, especially for use in multilingual spoken dialogue systems. We investigate different approaches to the acoustic modelling of Sepedi affricates for ASR. We determine that it is possible to model various of these complex consonants as a sequence of much simpler sounds. This approach reduces the Sepedi phoneme inventory from 45 to 32, resulting in simpler dictionary development and transcription processes, as well as more accurate acoustic modelling.
Description: 2010 Annual Research Conference of the South African Institute for Computer Scientists and Information Technologists (SAICSIT 2010), Bela Bela, South Africa, 11-13 October 2010. This is an ABSTRACT ONLY
URI: http://delivery.acm.org/10.1145/1900000/1899552/p394-modipa.pdf?ip=146.64.81.8&acc=ACTIVE%20SERVICE&CFID=88545526&CFTOKEN=51832324&__acm__=1331025181_6c0810155717926dddd97de90a1b4bf0
http://hdl.handle.net/10204/5631
ISBN: 978-1-60558-950-3
Appears in Collections:Human language technologies
General science, engineering & technology

Files in This Item:

File Description SizeFormat
Modipa_2010.pdf_ABSTRACT ONLY.pdf49.77 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