Keyword Search:

Bookmark and Share

Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition

Seman, Noraini and Jusoff, Kamaruzaman (2008) Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition. Computer and Information Science, 1 (4). pp. 112-120. ISSN 1913-8989

Full text not available from this repository.

Official URL:


This paper presents different methods of handling pronunciation variations in Standard Malay (SM) speech recognition. Pronunciation variation can be handled by explicitly modifying the knowledge sources or improving the decoding method. Two types of pronunciation variations are defined, namely, complete or phone changes and partial or sound changes. Complete or phone change means that one phoneme is realized as another phoneme. Meanwhile, a partial or sound change happens when the acoustic realization is ambiguous between two phonemes. Complete or phone changes can be handled by constructing a pronunciation variation dictionary to include alternative pronunciations at the lexical level or dynamically expanding the search space to include those pronunciation variants. Sound or partial changes can be handled by adjusting the acoustic models through sharing or adaptation of the Gaussian mixture components. Experimental results show that the use of a pronunciation variation dictionary and the method of dynamic search space expansion can improve speech recognition performance substantially. The methods of acoustic model refinement were found to be relatively less effective in our experiments.

Item Type:Article
Keyword:Pronunciation variations, Standard Malay (SM), Complete changes, Partial Changes
Faculty or Institute:Faculty of Forestry
ID Code:7628
Deposited By: Norhazura Hamzah
Deposited On:03 Aug 2010 14:41
Last Modified:03 Aug 2010 14:44

Repository Staff Only: Edit item detail

Document Download Statistics

This item has been downloaded for since 03 Aug 2010 14:41.

View statistics for "Acoustic Pronunciation Variations Modeling for Standard Malay Speech Recognition"