Improving ASR performance using context-dependent phoneme model
Purpose – The purpose of this paper is to present evidence of the need to have a carefully designed lexical model for speech recognition for dyslexic children reading in Bahasa Melayu (BM). Design/methodology/approach – Data collection is performed to obtain the most frequent reading error patter...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Emerald Group Publishing
2010
|
| Subjects: | |
| Online Access: | https://repo.uum.edu.my/id/eprint/1319/1/Zulikha%2CJ_Improving_ASR%5B1%5D.pdf |
| _version_ | 1825739782599213056 |
|---|---|
| author | Husni, Husniza Jamaludin, Zulikha |
| author_facet | Husni, Husniza Jamaludin, Zulikha |
| author_sort | Husni, Husniza |
| collection | UUM |
| description | Purpose – The purpose of this paper is to present evidence of the need to have a carefully designed
lexical model for speech recognition for dyslexic children reading in Bahasa Melayu (BM).
Design/methodology/approach – Data collection is performed to obtain the most frequent reading
error patterns and the reading recordings. Design and development of the lexical model considers the
errors for better recognition accuracy.
Findings – It is found that the recognition accuracy is increased to 75 percent when using contextdependent
(CD) phoneme model and phoneme refinement rule. Comparison between contextindependent phoneme models and CD phoneme model is also presented.
Research limitations/implications – The most frequent errors recognized and obtained from data
collection and analysis illustrate and support that phonological deficit is the major factor for reading
disabilities in dyslexics.
Practical implications – This paper provides the first step towards materializing an automated
speech recognition (ASR)-based application to support reading for BM, which is the first language in Malaysia.
Originality/value – The paper contributes to the knowledge of the most frequent error patterns for dyslexic children’s reading in BM and to the knowledge that a CD phoneme model together with the phoneme refinement rule can built up a more fine-tuned lexical model for an ASR specifically for dyslexic children’s reading isolated words in BM. |
| first_indexed | 2024-07-04T05:15:19Z |
| format | Article |
| id | uum-1319 |
| institution | Universiti Utara Malaysia |
| language | English |
| last_indexed | 2024-07-04T05:15:19Z |
| publishDate | 2010 |
| publisher | Emerald Group Publishing |
| record_format | eprints |
| spelling | uum-13192010-10-14T07:32:06Z https://repo.uum.edu.my/id/eprint/1319/ Improving ASR performance using context-dependent phoneme model Husni, Husniza Jamaludin, Zulikha LC Special aspects of education QA75 Electronic computers. Computer science Purpose – The purpose of this paper is to present evidence of the need to have a carefully designed lexical model for speech recognition for dyslexic children reading in Bahasa Melayu (BM). Design/methodology/approach – Data collection is performed to obtain the most frequent reading error patterns and the reading recordings. Design and development of the lexical model considers the errors for better recognition accuracy. Findings – It is found that the recognition accuracy is increased to 75 percent when using contextdependent (CD) phoneme model and phoneme refinement rule. Comparison between contextindependent phoneme models and CD phoneme model is also presented. Research limitations/implications – The most frequent errors recognized and obtained from data collection and analysis illustrate and support that phonological deficit is the major factor for reading disabilities in dyslexics. Practical implications – This paper provides the first step towards materializing an automated speech recognition (ASR)-based application to support reading for BM, which is the first language in Malaysia. Originality/value – The paper contributes to the knowledge of the most frequent error patterns for dyslexic children’s reading in BM and to the knowledge that a CD phoneme model together with the phoneme refinement rule can built up a more fine-tuned lexical model for an ASR specifically for dyslexic children’s reading isolated words in BM. Emerald Group Publishing 2010 Article PeerReviewed application/pdf en https://repo.uum.edu.my/id/eprint/1319/1/Zulikha%2CJ_Improving_ASR%5B1%5D.pdf Husni, Husniza and Jamaludin, Zulikha (2010) Improving ASR performance using context-dependent phoneme model. Journal of Systems and Information Technology, 12 (1). pp. 56-69. ISSN 1328-7265 http://www.emeraldinsight.com/1328-7265.htm |
| spellingShingle | LC Special aspects of education QA75 Electronic computers. Computer science Husni, Husniza Jamaludin, Zulikha Improving ASR performance using context-dependent phoneme model |
| title | Improving ASR performance using context-dependent phoneme model |
| title_full | Improving ASR performance using context-dependent phoneme model |
| title_fullStr | Improving ASR performance using context-dependent phoneme model |
| title_full_unstemmed | Improving ASR performance using context-dependent phoneme model |
| title_short | Improving ASR performance using context-dependent phoneme model |
| title_sort | improving asr performance using context dependent phoneme model |
| topic | LC Special aspects of education QA75 Electronic computers. Computer science |
| url | https://repo.uum.edu.my/id/eprint/1319/1/Zulikha%2CJ_Improving_ASR%5B1%5D.pdf |
| work_keys_str_mv | AT husnihusniza improvingasrperformanceusingcontextdependentphonememodel AT jamaludinzulikha improvingasrperformanceusingcontextdependentphonememodel |