Pronunciation variations and context-dependent model to improve ASR performance for dyslexic children’s read speech
Focusing on the key element for an ASR-based application for dyslexic children reading isolated words in Bahasa Melayu, this paper can be an evidence of the need to have a carefully designed acoustic model for a satisfying recognition accuracy of 79.17% on test dataset. Pronunciation variations and...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2009
|
| Subjects: | |
| Online Access: | http://repo.uum.edu.my/13594/1/PID261.pdf http://repo.uum.edu.my/13594/ http://www.icoci.cms.net.my |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Focusing on the key element for an ASR-based application for dyslexic children reading isolated words in Bahasa Melayu, this paper can be an evidence of the need to have a carefully designed acoustic model for a satisfying recognition accuracy of 79.17% on test dataset. Pronunciation variations and context-dependent model are two main components of such acoustic model. This model adopts the most frequent errors in reading selected vocabulary, which are obtained from primary data collection and analysis.The analysis gives the most frequent spelling and reading errors as vowel substitution with over 20% of total errors made. |
|---|