封面图片

Automatic transcription and segmentation accuracy of dyslexic children’s speech

Highly phonetically similar reading mistakes often occur when dyslexic children read. In respect to automatic speech transcription, these mistakes are challenging, even for manual transcription.The highly phonetically similar reading mistakes are difficult to be recognized, not to mention segmenting...

全面介绍

Saved in:
书目详细资料
Main Authors: Husni, Husniza, Nik Him, Nik Nurhidayat, Radi, Mohamad M., Yusof, Yuhanis, Kamaruddin, Siti Sakira
格式: Article
语言:English
出版: IP Publishing LLC 2017
主题:
QA75 Electronic computers. Computer science
在线阅读:http://repo.uum.edu.my/25655/1/AIP%20CP%201891%202017%201%206.pdf
http://repo.uum.edu.my/25655/
http://doi.org/10.1063/1.5005387
标签: 添加标签
没有标签, 成为第一个标记此记录!
id my.uum.repo.25655
record_format eprints
spelling my.uum.repo.256552019-02-24T07:56:16Z http://repo.uum.edu.my/25655/ Automatic transcription and segmentation accuracy of dyslexic children’s speech Husni, Husniza Nik Him, Nik Nurhidayat Radi, Mohamad M. Yusof, Yuhanis Kamaruddin, Siti Sakira QA75 Electronic computers. Computer science Highly phonetically similar reading mistakes often occur when dyslexic children read. In respect to automatic speech transcription, these mistakes are challenging, even for manual transcription.The highly phonetically similar reading mistakes are difficult to be recognized, not to mention segmenting and labelling them accordingly for processing prior to training speech recognition (ASR). The need to automate the segmentation and labelling arise especially when we need to build an ASR for assisting dyslexic children’s reading. Hence, the aim of this paper is to investigate the effects that highly phonetically similar errors have upon transcription and segmentation accuracy. A total of 585 speech files are used to produce manual transcription, forced alignment, and training. The recognition of ASR engine using automatic transcription and phonetic labelling obtained 76.04% accuracy with 23.9% word error rate and 18.1% false alarm rate. The results are almost similar with its manual counterpart with 76.26% accuracy, 23.7% word error rate and 17.9% false alarm rate. IP Publishing LLC 2017 Article PeerReviewed application/pdf en http://repo.uum.edu.my/25655/1/AIP%20CP%201891%202017%201%206.pdf Husni, Husniza and Nik Him, Nik Nurhidayat and Radi, Mohamad M. and Yusof, Yuhanis and Kamaruddin, Siti Sakira (2017) Automatic transcription and segmentation accuracy of dyslexic children’s speech. AIP Conference Proceedings, 1891. pp. 1-6. ISSN 0094-243X http://doi.org/10.1063/1.5005387 doi:10.1063/1.5005387
institution Universiti Utara Malaysia
building UUM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Utara Malaysia
content_source UUM Institutionali Repository
url_provider http://repo.uum.edu.my/
language English
topic QA75 Electronic computers. Computer science
spellingShingle QA75 Electronic computers. Computer science
Husni, Husniza
Nik Him, Nik Nurhidayat
Radi, Mohamad M.
Yusof, Yuhanis
Kamaruddin, Siti Sakira
Automatic transcription and segmentation accuracy of dyslexic children’s speech
description Highly phonetically similar reading mistakes often occur when dyslexic children read. In respect to automatic speech transcription, these mistakes are challenging, even for manual transcription.The highly phonetically similar reading mistakes are difficult to be recognized, not to mention segmenting and labelling them accordingly for processing prior to training speech recognition (ASR). The need to automate the segmentation and labelling arise especially when we need to build an ASR for assisting dyslexic children’s reading. Hence, the aim of this paper is to investigate the effects that highly phonetically similar errors have upon transcription and segmentation accuracy. A total of 585 speech files are used to produce manual transcription, forced alignment, and training. The recognition of ASR engine using automatic transcription and phonetic labelling obtained 76.04% accuracy with 23.9% word error rate and 18.1% false alarm rate. The results are almost similar with its manual counterpart with 76.26% accuracy, 23.7% word error rate and 17.9% false alarm rate.
format Article
author Husni, Husniza
Nik Him, Nik Nurhidayat
Radi, Mohamad M.
Yusof, Yuhanis
Kamaruddin, Siti Sakira
author_facet Husni, Husniza
Nik Him, Nik Nurhidayat
Radi, Mohamad M.
Yusof, Yuhanis
Kamaruddin, Siti Sakira
author_sort Husni, Husniza
title Automatic transcription and segmentation accuracy of dyslexic children’s speech
title_short Automatic transcription and segmentation accuracy of dyslexic children’s speech
title_full Automatic transcription and segmentation accuracy of dyslexic children’s speech
title_fullStr Automatic transcription and segmentation accuracy of dyslexic children’s speech
title_full_unstemmed Automatic transcription and segmentation accuracy of dyslexic children’s speech
title_sort automatic transcription and segmentation accuracy of dyslexic children’s speech
publisher IP Publishing LLC
publishDate 2017
url http://repo.uum.edu.my/25655/1/AIP%20CP%201891%202017%201%206.pdf
http://repo.uum.edu.my/25655/
http://doi.org/10.1063/1.5005387
_version_ 1644284387913629696
score 13.250435

相似书籍