• Anup A Saleem
• Rathila Ramesh
• Abhishek B.K
• Niveditha .S

There are many areas in computer science which have not used the resources around them optimally to their fullest potential. Such is the case of PDF to speech conversion in today's perspective. PDF to speech conversion is a problem which can be solved by dividing it in two halves. One half being PDF text extraction and the second one being text to speech conversion. PDF text extraction can be done using TexParsers, Although all the PDF files cannot be handled by just one Parser as the contents of a file may vary from texts to photos and other media. Also in text to speech conversion there are various locales for different regions for the English language, which can help increase the understand-ability of the converted speech. Using the fore mentioned tools and various other tools to handle exceptional cases, this project aims to fuse the functionality of these tools and produce an accurate PDF to Speech conversion system. We have compared our systems with other systems based on various criteria, such as, Processing speed, Accuracy and CPU usage. In accordance with processing speed the tool which we used, computed the same test cases in just 25% of the time used by the nearest fastest tool tested. In terms of CPU usage, our system uses around 10% less CPU Space than the next least space occupying tool tested. The OCR tool we integrated was compared to be the most accurate among two other competitors with the accuracy rate of 80%

PDF, TexParsers, Text to Speech

"PDF To Speech using TexParsing and Tokenization", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 3, page no.278-284, March-2019, Available :http://www.jetir.org/papers/JETIR1903F43.pdf

"PDF To Speech using TexParsing and Tokenization", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 3, page no. pp278-284, March-2019, Available at : http://www.jetir.org/papers/JETIR1903F43.pdf