Title: AraDaisy: a system for automatic generation of Arabic DAISY books

Authors: Iyad Abu Doush; Faisal Alkhateeb; Abdelraouf Albsoul

Addresses: Department of Computer Science, Yarmouk University, Irbid, Jordan ' Department of Computer Science, Yarmouk University, Irbid, Jordan ' Department of Computer Science, Yarmouk University, Irbid, Jordan

Abstract: A good library is one that has all of its resources accessible to all kinds of people, e.g. people with print disabilities. For this purpose, librarians try to provide books in several types of formats to accommodate different users. For example, e-books and digital talking books (DTB) are now available and can be used by a wider spectrum of users. Several systems can be found for transforming a book into DTB for people where the mother language is English. Such systems transform a book into DTB by encoding the document using DAISY format. However, Arabic DTBs are sparse since the work done so far in this domain is not well understood. In fact, Arabic language is very hard to process and such characteristics provide another complex dimension to a system that is able to transform an Arabic book into a DTB. In this paper, we propose a framework for an Arabic DTB that uses DAISY format. The proposed system includes an image-to-text converter, context-injector, text-to-audio-generator, and finally a DAISY generator. The implemented system is tested over ten users whose mother language is Arabic. The results were promising and we also provided a set of recommendations that can enhance the quality of the system.

Keywords: DAISY; digital talking books; OCR; optical character recognition; assistive technologies; print disabilities.

DOI: 10.1504/IJCAT.2017.086007

International Journal of Computer Applications in Technology, 2017 Vol.55 No.4, pp.322 - 333

Available online: 04 Aug 2017 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article