Loading presentation...

Present Remotely

Send the link below via email or IM

Copy

Present to your audience

Start remote presentation

  • Invited audience members will follow you as you navigate and present
  • People invited to a presentation do not need a Prezi account
  • This link expires 10 minutes after you close the presentation
  • A maximum of 30 users can follow your presentation
  • Learn more about this feature in our knowledge base article

Do you really want to delete this prezi?

Neither you, nor the coeditors you shared it with will be able to recover it again.

DeleteCancel

Make your likes visible on Facebook?

Connect your Facebook account to Prezi and let your likes appear on your timeline.
You can change this under Settings & Account at any time.

No, thanks

Copy of VOICE BASED EMAIL FOR BLINDS

No description
by

Sangeet Sagar

on 17 December 2014

Comments (0)

Please log in to add your comment.

Report abuse

Transcript of Copy of VOICE BASED EMAIL FOR BLINDS

VOICE BASED EMAIL
APPLICATION

VOICE BASED EMAIL APPLICATION
ABSTRACT
CONT...
It helps us to convert written English text to audio files and play them. The user can receive, compose and send a mail to another Voice mail system user. A Voice mail system user has an added benefit over other email systems because it provides an option for the user to read his mails aloud that are in their understandable language, reducing his strain.

Thus reliance of visually impaired on other people for their activities related to mail can be reduced. Dictation using speech recognition could potentially serve as an efficient input method for mailing devices for blind.
PROBLEM STATEMENT
Outdoor communication is becoming a harder task for blind and visually impaired people in the complex urban world.

Advances in technology are causing the blind to fall behind, sometimes even putting their lives at risk.

Lot of confidential and urgent information are exchanged over e-mails in today’s time. This puts the visually impaired people at a certain disadvantage.



EXISTING SYSTEM
Audio feedback based virtual environment like, the screen readers have helped Blind people to access internet applications. Voice recognition systems have been deployed in desktops and smartphones. Making calls, opening apps within phones are some important implications of it.

Voice enabled search (by Google and various others) is also an existing application of speech synthesizing.Asking for directions while driving and hearing the response through speech synthesis illustrates how practical "hands-free" applications can be to mobile users.



THANK YOU
Samarth Rastogi 4NI11IS096
Sangeet Sagar 4NI11IS097
Tushar Garg 4NI11IS118
Vaibhav Awasthi 4NI11IS120
Designing a Voice Mail system architecture.

The speech synthesis embedded in Voice mail system can read aloud any written text, avoiding eye strain and save time, reading on the computer. This is a web based system developed using HTML and java. It can be employed as an aid for the people who suffer with visual impairment.

SCOPE OF THE PROJECT
LIMITATIONS
IMPLEMENTATION OVERVIEW
Real time composition of textual mail through audio input.

Use of keywords to trigger particular mail related operations.

Audio output of recieved mail.

Need to hard code dialogue specifications.

Need to predict dialogue possibilities.

Sometimes Speech Recognition Software is that it can not understand all the words we speak even after hours of training.

CONT..
Software Requirements:

Developed speech recognition system target to be run on any platform which comprises the JavaRuntime Environment (JRE). For running this application user should add Java Speech API library set for the system. Also there should be some storage mechanism which will describe in detail on the design document.

• Framework : JSAPI
• Language : JAVA
• Operating System : Windows X/vista/windows 7.

SYSTEM REQUIREMENTS
Hardware Requirements:
2 GB RAM
250 GB HDD
2.10 Clock Speed (CPU Time)
Microphone
Sound cards with very clear signals
High quality microphones
Project Guide: Kuzhalvaimozhi S
user
Microphone
Process the voice using API
Speech recognition engine
Speech aware application
What time it is
LITERATURE SURVEY
The advancement in computer based accessible systems has opened up many avenues for the visually impaired across a wide majority of the globe. Audio feedback based virtual environment like, the screen readers have helped Blind people to access internet applications immensely.

However, a large section of visually impaired people in different countries in particular, the Indian sub-continent could not benefit much from such systems. This was primarily due to the difference in the technology required for Indian languages compared to those corresponding to other popular languages of the world,

CONT...
Consider the browser and its settings
When scripting a web-based application, tailor macros to one browser. It may even be necessary to script for a particular version (or versions) of a browser.

Browser settings affect script performance. Features such as user preferences, browser tabs, toolbars, add-ins, and extensions may change the appearance, layout, and behaviour of pages. Some settings help while others hinder. Keep browser settings in mind when developing voice macros for web-based applications, and document the necessary browser settings.

CONT...
Create substitutes for unreliable NaturallySpeaking commands
Do not hesitate to script substitutes for unreliable commands. Because "list," "link" and similar commands frequently failed, its easy to create easy-to-remember substitutes such as "Show Buttons," Show Lists," and "Show Links." All can be created using Advanced Scripting or hard coding frequently used words. Thus, the interaction with the browser tools for reaching the E-mail servers is a task at hand after the speech synthesizing part is done.
CONT...
Pattern Recognition Approach
In this approach, the speech patterns are used directly without explicit feature determination and segmentation. The method has two steps-namely, training of speech patterns, and recognition of patterns by way of pattern comparison. Figure 2 shows a block diagram of the pattern-recognition approach. In the parameter measurement phase, a sequence of measurements is made on the input signal to define the “test pattern”. The unknown test pattern is then compared with each sound reference pattern and a measure of similarity between the test pattern and reference pattern is computed. Finally the decision rule decides which reference pattern best matches the unknown test pattern based on the similarity scores from the pattern classification phase.
Pattern Recognition Approach
reference
pattern
parameter
measurement
pattern
comparison
decision rule
recognised speech
speech
test
pattern
PROPOSED SYSTEM
Dictation using speech recognition could potentially serve as an efficient input method for mailing devices for blind.
However, dictation systems follows a speech interaction model Voice Typing aspires to create an experience to having a secure type.
This project is designed using some set of JAVA APIs.
The speech recognition system design will involve pattern search algorithm which will constitute of parsing grammar , lexical, keywords which will generate a text string automatically after implementing some decision rules.

ALGO USED FOR SPEECH RECOGNITION
Hidden Markov Model (H.M.M)

HMMs allow you to estimate probabilities
of unobserved events. The Hidden Markov Model is a finite set of states, each of which is associated with a probability distribution. Transitions among the states are governed by a set of probabilities called transition probabilities. In a particular state an outcome or observation can be generated, according to the associated probability distribution. It is only the outcome, not the state visible to an external observer and therefore states are "hidden'' to the outside; hence the name Hidden Markov Model.


CONT...
This process is even more complicated
for phrases and sentences -- the system has to figure out where each word stops and starts. The classic example is the phrase "recognize speech," which sounds a lot like "wreck a nice beach" when you say it very quickly. The program has to analyze the phonemes using the phrase that came before it in order to get it right. Here's a breakdown of the two phrases:

r eh k ao g n ay z s p iy ch
"recognize speech"
r eh k ay n ay s b iy ch
"wreck a nice beach"

Why is this so complicated? If a program has a vocabulary of 60,000 words (common in today's programs), a sequence of three words could be any of 216 trillion possibilities. Obviously, even the most powerful computer can't search through all of them without some help.

DATA FLOW DIAGRAM
DFD level 0
Input Speech
Process
Speech
text output
Input speech
Error message
display text
DFD level 1
Process
voice
engine
if not found
if found and matched
Display text
error msg
Input
speech
process
speech
digital
signal
process digital
signal
generate
probability
match
voice
database
process
database
engine
if match found
if not found
search probability match in database
convert to digital signal
using AFR filter
DFD level 2
CONTD...
Full transcript