Voice search for Quranic verses recitation

Abstract

This paper describes challenges and solutions for building a successful voice search system as applied to Quranic verses. The paper describes the techniques used to deal with an finite vocabulary how modelling completely in the voice domain for language model and dictionary can avoid some system complexity, and how we built dictionaries, language and acoustic models in the framework. The Holy Quran is written in Arabic language, and the Arabic is one of the oldest languages In the world that presents its own features and challenges while searching for Arable-based content. The most search systems for the Holy Quran Is organized around text words (contained in the target verses) but no system organized around voice while there is need to search in quranic recitation. The speech recognition approaches are applied to build the dictionary and test the system, while the MFCC and stemming techniques will be will be applied to find the stem of the word. The development of voice search for Quranic recitation led to a significant simplification of the original process to build a system to retrieving audio information related to the Qur'an, it also helps to build a system to serve people with special needs such as bllnd,paralyzed, and others who can not use the keyboard.