A system for the conversion of digital Gujarati text-to-speech for visually impaired people

Abstract

In the epoch of hi-tech development, study on Text-to-Speech conversion shows remarkable enhancement in last couple of decades. Visually impaired people are not able to read, so Text-to-Speech system acts as an aid for visually impaired people for reading by hearing the text. In this paper, we presented the development of computer-based Gujarati Text-to-Speech system that delivers text in Gujarati audio form. Arbitrary digital Gujarati text is considered as an input to the system; conversion is done with regard to the Akshara of Gujarati language, and sound is produced in the form of phoneme, diphone, or syllable as per the requirement. Single audio file is created of the text so that it can also be heard at later stage. The detailed algorithm along with the format of speech database is also presented in the paper. Proposed system is tested on the documents collected from online news Web site and it gives satisfactory result.