You are on page 1of 2

Python-Text-To-Speech

The idea of this paper is to build an automatedvirtual reader. In this modern era, there is an urge
for an automated reader which is cost-effective, accurate and also portable at the same time. The
product is based on a Raspberry Pi module that also has a camera connected to it which is used
to take pictures. The whole bodywork is also integrated with Optical Character Recognition
(OCR), Text-To-Speech (TTS) and a speaker. A Graphical User Interface (GUI) helps the users
to take pictures with the help of a single click. A button is also integrated with the Raspberry Pi
which helps initiate the program and carry out all the functions. After the successful capturing of
the picture, the system carries out some basic image processing black and white conversion and
de-noising. The processed image is then supplied to the Tesseract-OCR which understands the
characters and TTS is used to convert the text to audio format. A software named eSpeak is used
to read out the audio formatted file which is delivered as an output with the help of a speaker.
Conversion of text to speech can also be done in Matlab but that wouldn’t be portable and user-
friendly.Speech recognition is useful in various appliances around us like Google Assistant,
Alexa, Cortona etc. Speech recognition has made things easy like we can use our voice to talk to
google assistants and find the answers to our questions.

EXISTING SYSTEM:
Speech is the most natural, convenient and widespread communication interface for humans with
either humans or machines via different languages. Language is a systematic means for
communication through the use of speech or conventional symbols for each one. Language
processing is a very promising area that can take speech processing into data processing based on
applied linguistics for advancing human interfaces connecting the whole universe. Applied
linguistics is the study of language for the purpose of addressing real-life problems concerning
language systems and their use. The most common concerns of specialists in this area include
language teaching, translation studies and investigations into artificial intelligence. The
applications and findings within this realm are derived from studies into the nature of language.
DISADVANTAGES OF EXISTING SYSTEM:

Algorithm: Text to Speech (TTS) Converters, basic understanding of the Tkinter, pyttsx3, and
speech recognition libraries.

PROPOSED SYSTEM: This software project is a windows based software that reads a text file
to the user. The bot reads a text file and associated pronunciations in its temporary database. The
bot then reads an entire word to the user. The pronunciations of articles and basic words have
been fed to the bot, the rest of the words and complex ones are calculated and read accordingly.
The bot an be effectively used to help read the text document for the user so that the user does
not constantly need to look at the screen and read the entire document. Test to speech converter
is a recent software project that allows even the visually challenged to read and understand
various documents.
ADVANTAGES OF PROPOSED SYSTEM:
 The system is helpful for persons having learning disabilities or visually challenged.
 Prevents eye from strain, and user can sit and listen comfortably.
 Saves time especially while driving, exercising.
 Easy to use.
 Help improving spelling, reading, writing skills.

Algorithm: Convolutional Neural Network; Data Augmentation Deep Learning.


HARDWARE REQUIREMENTS:

System : Intel i5 6 core.


Hard Disk : 500 GB SSD.
Monitor : 15’’ LED
Input Devices : Keyboard, Mouse
Ram : 32 GB.

You might also like