Husni, Husniza and Jamaludin, Zulikha (2010) Minimizing word error rate in a dyslexic reading-oriented ASR engine using phoneme refinement and alternative pronunciation. In: EDULEARN10 Proceedings CD. IATED publication, Madrid. ISBN 9788461393862 (In Press)
PDF (Abstract view)
Download (12kB) |
Abstract
Little attention has been given to detecting miscues in the text space read by dyslexic children over an automatic speech recognition (ASR) engine. In an ASR system, the miscues are represented by word error rate (WER) and miscue detection rate (MDR). At all time, WER must be kept low, and MDR high so as to achieve better recognition. This paper focus on minimizing word error rate by formulating a better model for perspicuous representation of input data. Such representation takes into account phoneme refinement and alternative pronunciation for a particular Bahasa Melayu (BM) speech data uttered by dyslexic children. Based on literature, a few other optimal models of input data and their recognition results were compared. It is found that phoneme refinement and alternative pronunciation produced better recognition results as evidenced in the performance metrics --lower WER and higher MDR-- which are 25% and 80.77% respectively.
Item Type: | Book Section |
---|---|
Additional Information: | Third Annual Edition of ICERI 2010 (International Conference of Education, Research and Innovation) that will be held in Madrid (Spain) on the 15th - 17th of November, 2010. |
Uncontrolled Keywords: | Automatic speech recognition, miscue detection, phoneme refinement, dyslexic children reading |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science |
Divisions: | UNSPECIFIED |
Depositing User: | Prof. Dr. Zulikha Jamaludin |
Date Deposited: | 17 Oct 2010 07:28 |
Last Modified: | 17 Oct 2010 07:34 |
URI: | https://repo.uum.edu.my/id/eprint/1339 |
Actions (login required)
View Item |