排序方式： 共有5条查询结果，搜索用时 15 毫秒
1
1.
ASR technology for children with dyslexia： Enabling immediate intervention to support reading in Bahasa Melayu 总被引：1，自引：0，他引：1
Husniza Husni Zulikha Jamaludin 《美中教育评论》2009,6(6):64-70
Reading is an essential skill towards literacy development, and should be provided so that children can master the skill at their early ages. For dyslexic children, mastering the skill is a challenge. It has been widely agreed that the theory behind such difficulties in reading for dyslexic lies in the phonological-core deficits. Support has been given in many ways to dyslexic children to teach them reading through using various multi-sensory methods and using computer-based applications that include animated characters and text-to-speech （TTS） technology. In such applications, although stimulating, it requires the children to call for help by clicking on the custom-made buttons on the computer screen, often, such an application requires the dyslexic children to be aware of their mistakes and be able to judge when help is needed. They are just reluctant to ask the computer for help. Hence, such technology does not provide immediate intervention to correct any reading failure. It is therefore worth to look at the promising automatic speech recognition （ASR） technology to provide such intervention. Hence, this paper gives an overview of the use of ASR to facilitate immediate reading intervention which is the key element of remediating reading among dyslexic children. For such intervention to work, data on reading mistakes and patterns are observed and collected in audio format. The data serve as training and testing samples for an ASR to train on. An observation was carried out in two public schools participated in the study to record dyslexic children＇s reading in Bahasa Melayu （BM） and observe error patterns and their behaviors toward reading. A total of 10 dyslexic children are involved and a total of 6384 utterances from a set of selected words have been gathered and analyzed. Data are grouped into error type categories and the analysis performed gives ＂vowel substitution＂ as the most frequent error made （20%）. The significant findings can be of interest of special education teachers or parents to devise and use suitable approach to correct reading mistakes often made by dyslexic children. The findings also contribute to the development of a suitable and well-tuned ASR model focusing on dyslexic children reading aloud in BM. 相似文献
2.
The magazine industry has succumbed to severe cutbacks in recent months but nevertheless is still a vibrant industry. In order
to become a successful part of this industry, magazines must go through certain stages of life in which they meet with certain
challenges. Surviving these stages is the mark of a truly auspicious publication, but surviving also means being able to adapt
to market and readership changes. 相似文献
3.
Arabic is a widely spoken language but few mining tools have been developed to process Arabic text. This paper examines the crime domain in the Arabic language (unstructured text) using text mining techniques. The development and application of a Crime Profiling System (CPS) is presented. The system is able to extract meaningful information, in this case the type of crime, location and nationality, from Arabic language crime news reports. The system has two unique attributes; firstly, information extraction that depends on local grammar, and secondly, dictionaries that can be automatically generated. It is shown that the CPS improves the quality of the data through reduction where only meaningful information is retained. Moreover, the Self Organising Map (SOM) approach is adopted in order to perform the clustering of the crime reports, based on crime type. This clustering technique is improved because only refined data containing meaningful keywords extracted through the information extraction process are inputted into it, i.e. the data are cleansed by removing noise. The proposed system is validated through experiments using a corpus collated from different sources; it was not used during system development. Precision, recall and F-measure are used to evaluate the performance of the proposed information extraction approach. Also, comparisons are conducted with other systems. In order to evaluate the clustering performance, three parameters are used: data size, loading time and quantization error. 相似文献
4.
Samir A. Husni 《Journal of Media Economics》2013,26(1):39-49
This study tracks magazines started from 1981 to 1983 that have survived to the present. It finds that magazines started by entrepreneurs, rather than media firms, and magazines that were consumer driven, rather than advertising driven, were more likely to survive. 相似文献
5.
1