Design and Implementation of Voice Based Email System for Blinds
Chapter One
OBJECTIVE OF THE STUDY
The main objective of this project is to create an IVR- interactive voice response email system. When using this system the computer will be prompt the user to perform specific operations to avail respective services and if the user needs to access the respective services then he/she needs to perform that operation. The new system will be designed in such a way that the user won’t require to use the keyboard alot.
CHAPTER TWO
LITERATURE REVIEW
INTRODUCTION
The Speech is the most common & primary mode of communication among human beings. It is the most natural and efficient form of exchanging information among humans . Human voice conveys much more information such as gender, emotion and identity of the speaker. Speech Recognition can be defined as the process of converting speech signal to a sequence of words by means an Algorithm.
The objective of speech recognition is to determine which speaker is present based on the individual’s characterization (Cheong and abdul, 2008). Several techniques have been proposed for compensating the mismatch occurred between the testing and training sessions. The communication among human computer interaction is called human computer interface.
Since 1960s computer scientists have been researching ways and means to make computers able to record, interpret and understand human speech. In computer science, speech recognition (SR) is the translation of spoken words into text. It is also known as “automatic speech recognition”, “ASR”, “computer speech recognition”, “speech to text”, or just “STT”.
Speaker recognition is the identification of the person who is speaking by characteristics of their voices (voice biometrics), also called voice recognition.
CLASSIFICATION OF SPEECH
A number of parameters define the capability of a speech recognition system.( http://crdo.up.univ aix.fr/ExternalDisk0/preview/000836/node303.html)
- Isolated word: The Isolated word have sample windows.it accepts single word or single utterances at a time. Isolated utterance might be a better name of this work. (Zahi N.Karam,William)
- Connected word: The Connected word system are similar to isolated words but allow separate utterance to be “run together minimum pause between them.
- Continuous speech :It allows user to speak almost naturally, while the computer will examine the content.there are special methods used to determine utterance boundaries and various difficulties occurred in it.
- Spontaneous speech: A System with spontaneous speech ability should be able to handle a variety of natural speech feature such as words being run together.
SPEECH RECOGNITION TECHNIQUES
The goal of speech recognition is to analyze, extract, characterize and recognize information about the speaker identity. Variety of the techniques are used for determining the speech characteristics.
Speech analysis technique
The speech data contain different type of information that shows the speaker identity. This includes speaker specific information due to vocal tract, excitation source and behavior feature. The speech analysis stage deals with stage with suitable frame size for segmenting speech signal for further analysis and extracting. (Gin-Der Wu and Ying Lei). These are of three types.
CHAPTER THREE
SYSTEM DESIGN AND ANALYSIS
INTRODUCTION
System Analysis and Design involves ascertaining the objectives and problems of the existing system, and proper analysis carried out on facts gathered. Furthermore, the design of this study is to explain the method applied for the successfulness of the work. The need to have this work determined is to provide direction for the researches in order to enable the researcher achieve the objective of this project work. In contrast, this chapter is based on the work carried out by the researcher on how the conventional method of operation works.
SYSTEM ANALYSIS
System analysis can be simplified here as a detailed inquiry carried out by the system analysis to identify a better course of action and make a better decision on the proposed system.
CHAPTER FOUR
SYSTEM IMPLEMENTATION
INTRODUCTION
In this chapter, the development and implementation of the new system were discussed, included in this chapter were the change over method adopted, the choice of programming languages used in designing of the program and minimum system requirements for the hardware and software for proper functionality of the program.
CHAPTER FIVE
SUMMARY, CONCLUSION AND RECOMMENDATIONS
SUMMARY
Voice-based email system is a speech recognition software that converts spoken word to text by analyzing and processing the text using Natural Language Processing (NLP) and then using Digital Signal Processing (DSP) technology to convert this processed speech into representation of the text. This system will help in overcoming some drawbacks that were earlier faced by the blind people in accessing emails. I have eliminated the concept of using keyboard shortcuts along with screen readers which will help to reduce the cognitive load of remembering keyboard shortcuts. Also any naive user who does not know the location of keys on the keyboard need not worry as keyboard usage is eliminated. The user only needs to follow the instructions given by the IVR and use mouse clicks accordingly to get the respective services offered. Other than this the user might need to feed in information through voice inputs when specified.
CONCLUSION
Speech synthesis has long been a vital assistive technology tool and its application in this area is significant and widespread. It allows environmental barriers to be removed for people with a wide range of disabilities. The longest application has been in the use of screen readers for people with visual impairment, but speech-to-text systems are now commonly used by people with dyslexia and other reading difficulties as well as by pre-literate children. They are also frequently employed to aid those with severe speech impairment usually through a dedicated voice output communication aid. In recent years, Speech recognition tools for disability and handicapped communication aids has become widely deployed in Mass Transit. Speech-to-text is also finding new applications outside the disability market. For example, speech synthesis, combined with speech recognition, allows for interaction with mobile devices via natural language processing interfaces
RECOMMENDATIONS
This software is recommended to all visually impaired users who are computer literate and they are adviced to use this software, so that they can send emails without the help of any one. We therefore simply recommend the implementation of the project work for institution that are teaching blind people to make use of this Speech-to-text application for the benefit for their students. Finally, we recommend this project to the government to create awareness for this project so that the blind people will the know that this kind of application exists and can help them user computer applications with ease.
REFERENCES
- Cheong Soo Yee and abdul Manan ahmad, Malay Language Text Independent Speaker Verification using NN‐MLP classifier with MFCC, 2008 international Conference on Electronic Design.
- http://crdo.up.univ aix.fr/ExternalDisk0/preview/000836/node303.html
- Zahi N.Karam,William M.Campbell “A new Kernel for SVM MIIR based Speaker recognition “MIT Lincoln Laboratory, Lexington, MA, USA.
- Gin-Der Wu and Ying Lei “ A Register Array based Low power FFT Processor for speech recognition”Department of Electrical engineering national Chi Nan university Puli ,545 Taiwan.
- Nicolás Morales1, John H. L. Hansen2 and Doorstep T. Toledano1 “MFCC Compensation for improved recognition filtered and band limited speech” Center for Spoken Language Research, University of Colorado at Boulder, Boulder (CO), USA.
