Scribd
Upload
23 views

Uday PPT

This document describes a mini project on an audio to sign language translator. It aims to design a system to help people with hearing/speech disabilities by converting voice input in Indian sign language (ISL). The system would use speech recognition and image processing to recognize audio and translate it to sign language images/videos. It aims to overcome issues with existing systems such as low accuracy in text to sign language conversion and being time consuming. The proposed system would use speech to text APIs to convert audio to text and deep learning algorithms like DNN to more quickly and accurately convert text to related sign language images/GIFs.

Uploaded by

kirsagar akash
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
23 views

Uday PPT

This document describes a mini project on an audio to sign language translator. It aims to design a system to help people with hearing/speech disabilities by converting voice input in Indian sign language (ISL). The system would use speech recognition and image processing to recognize audio and translate it to sign language images/videos. It aims to overcome issues with existing systems such as low accuracy in text to sign language conversion and being time consuming. The proposed system would use speech to text APIs to convert audio to text and deep learning algorithms like DNN to more quickly and accurately convert text to related sign language images/GIFs.

Uploaded by

kirsagar akash
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 11

SREYAS

INSTITUTE OF ENGINEERING AND TECHNOLOGY


(Approved by AICTE, New Delhi | Affiliated to JNTUH, Hyderabad |
Accredited by NAAC)
Hyderabad | PIN: 500068

A MINI PROJECT
On
AUDIO TO SIGN LANGUAGE TRANSLATOR
BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND ENGINEERING
BY
B.SUMA - 20VE1A0564
D.UDAY KIRAN CHARY- 20VE1A0570
D.UJJWAL-20VE1A0573
N.SANDEEP-20VE1A0597

Under the Guidance of


Mrs.JOSHI PADMA – ASSISTANT PROFESSOR
ACADEMIC BATCH: (2020-2024)
AUDIO TO SIGN
LANGUAGE
TRANSLATOR
CONTENTS
• Abstract
• Problem Statement
• Existing System
• Disadvantages
• Proposed System
• Advantages
• Literature Survey
• Queries
ABSTRACT:
• The prevalence of deafness in India is fairly significant. It is the
second most common cause of disability.

• The aim of this paper is to design a system which is helpful for


the people with hearing / speech disabilities and convert a voice
in Indian sign language (ISL).

• The task of learning a sign language can be cumbersome for


people so this paper proposes a solution to this problem using
speech recognition and image processing.

• It is very difficult to normal person as well as disability persons


in order to communicate with people .
PROBLEM STATEMENT:
• Approximately 63 million people in India suffer from significant auditory loss.

• We h ave m o re t h a n 3 0 0 s i g n l a n g u a ge s a re u s i n g i n wo r l d t o d ay.

• It is hard for such individuals to express themselves since every one is not familiar with
sign language.

• In this project we propose a real-time system that recognizes the voice input through
pyaudio and Google API and converts it into text followed by GIF’s and Motioned videos .
EXISTING SYSTEM:
• Previous approaches were capable to recognize the speech
and convert the input audio into text using Natural
Language Processing algorithms .

• The existing systems focus on the translation by each letter


in a word and translates to American Sign Language
(ASL).

• It is difficult for the Indian deaf people to understand other


countries sign language like American Sign
Language(ASL), British Sign Language (BSL), New
Zealand Sign Language, and many more.
DISADVANTAGES:

• Less Acccuracy in Converting the text to (GIF's).


• Low Efficiency.
• More time taken to process the output
PROPOSED SYSTEM:
• Our proposed system is designed to overcome the
troubles faced by the deaf people.

• This system is designed to translate each word that


is received as input into sign language.

• Our system uses speech to text API to convert audio


to text and deep learning algorithms like deep
neural networks(DNN) to convert text to sign
language with the related signs(GIF’s).
ADVANTAGES:

• The functioning of the proposed system is fast

• With the help of DNN the identification of text


related signs becomes easy and accurate.
LITERATURE SURVEY:
SI.NO Author Name of paper Methodology

1) Khalid Khalil El Speech to Sign Language System uses digital image processing techniques and
DarymLi Interpreter System (SSLIS ). Artificial Neural Network(ANN) for recognizing
(January 2006) different signs.

2) Raj Kumar Speech To Sign Language System using Natural Language Processing(NLP)
(28 April 2018) Translator For Hearing Impaired. algorithms for finger spelling in Indian sign
Language(ISL) to text.

3) George E. Dahl, Dong Large vocabulary continuous Deep learning models in recognising continuous sign
Yu, Li Deng, Alex Acero speech recognition. languages.
( Nov 2020)
Queries

You might also like