Abstract

Document files are files used to store documents on storage
devices primarily for computer use. Software is used to view these files,
displaying their text content in a legible way. However, it is essential to have
programs for transforming electronic files into versions usable by those who
suffer from specific disabilities. This paper reviewed fifteen published articles
in the field of document file reading. It was observed from the review that
various attempts have been made by different researchers in order to develop
a software cable for converting document files that consist of text to an audio
format. Text may now be easily translated into natural-sounding voice across
many platforms using different software. It was observed from the systematic
review that the use of AI such as the GPT-3.5 and GPT-4 Turbo Large
Language Model (LLM) technologies has the best performance because it
does not end at producing a vocal sound that is similar to human own, but it
also translates different languages. In conclusion, cross-platform document
file reader (text-to-speech) synthesis has improved user experiences in a
variety of applications such as language learning, audiobooks and virtual
assistants.