Sunteți pe pagina 1din 5

Automated voice Response System

Abstract:
Automated Voice Response Systems (commonly abbreviated to AVRS) is another term for the more
common definition (interactive voice response). An Automated Voice Response system
(AVR) is the series of menu driven entries used to interface a computer with individuals over voice
phone connections. This is a computer telephony phone application and hardware that accepts voice input
and/or touch-phone keypad selection. An AVRS responds to this input by providing appropriate
information in the form of a voice answer (for example, by playing a wav file) or provides a connection to
a "live" operator. Another term for AVR is automated response unit, or ARU.

AVRS allows customers to access a company’s database via a telephone touchtone keypad or by
speech recognition, after which they can service their own enquiries by following the instructions. AVR
systems can respond with pre-recorded or dynamically generated audio to further direct users on how to
proceed. AVR systems can be used to control almost any function where the interface can be broken
down into a series of simple menu choices.

Project Scenario

The problem is to develop a generic framework for an Automated Voice Response System for
any business application, which will implement this framework, to provide services to the users
(customers) of the system.

It is advantageous to create a generic framework for such a system because any type of business
application can implement it with their corresponding requirements. The major modules involved in this
system are the phone, the modem, and the server. A connection has to be set up between these modules
for the voice interaction. The system can be incorporated with a GUI interface which will guide the
business applications to help them implement and set up the system. It would be a good solution to build
AVR services on a generic and large scale view, thus providing users with satisfying services.

Functionalities:
• Designing GUI for selecting keys

• Reading Text from Database

• Converting Text to Speech format

• Updating Database.

Technological Requirements:

Java 2 Standard Edition, Java Swings

Microsoft Windows, Linux or Mac any version

1. INTRODUCTION

1.1 Purpose
AVRS allows customers to access a company’s database via a telephone touchtone keypad or by speech
recognition, after which they can service their own enquiries by following the instructions. AVR systems
can respond with pre-recorded or dynamically generated audio to further direct users on how to proceed:

1.2 Project Scope


Automated Voice Response Systems (commonly abbreviated to AVRS) is another term for the more
common definition (interactive voice response). An Automated Voice Response system
(AVR) is the series of menu driven entries used to interface a computer with individuals over voice
phone connections. This is a computer telephony phone application and hardware that accepts voice input
and/or touch-phone keypad selection. An AVRS responds to this input by providing appropriate
information in the form of a voice answer (for example, by playing a wav file) or provides a connection to
a "live" operator. Another term for AVR is automated response unit, or ARU.

AVRS allows customers to access a company’s database via a telephone touchtone keypad or by
speech recognition, after which they can service their own enquiries by following the instructions. AVR
systems can respond with pre-recorded or dynamically generated audio to further direct users on how to
proceed. AVR systems can be used to control almost any function where the interface can be broken
down into a series of simple menu choices.

The main aim of the application is when the users are searching through an article in web, we wanted
some one to speak for the user instead he /she going through entire article. For that we wanted to build a
new concept of select and speak in IE. This is purely research and development in this area.
1.4 Project Description:
Text to speech program that lets you type-in any English or Spanish text and then plays it as an audio
stream.

Instantly convert desired text to speech

Converting files into Speech format .File can be doc, txt, pdf.

Supported language : English

Save converted text as an database.

2. PROBLEM DEFINITION

2.1 Existing System:


In the existing system we are getting the college information which is selected through notice board,
college communities or through various departments and through circulars ,websites etc.

2.2 Proposed System:


In proposed system we are accessing college information through automated voice response system which
is more user friendly.

2.3 User Classes and Characteristics

Using this product students can listen voice of entered choice . Administration can add new choices into
database or modify the existing choice.

2.1 The Operating Environment

SoftWare Requirements:

Software Requirements used are Windows XP and any other latest editions. JavaScript, Java
Technologies.

Hard Requirements:

Hardware Requirements used are P4processor, 512MB of Main Memory (RAM) and 40GB hard disk
and base memory.
2.2 Design and Implementation Constraints
Design constraints developers. All modules are coded thoroughly based on requirements from software
organization. The software is designed in such a way that the user can easily interact with the screen.
Software is designed in such a way that it can be extended to the real time business.

2.3 User Documentation


In our user manual we are going to keep the information regarding our product, which can be
understandable by a new person who is going to use it. If a new person is using it, online help will be
provided in that. We are going to explain each and every step clearly about our product so that any user
can easily understand it.

2.4 Module Description:

In this we have 4 modules

• Designing GUI for selecting keys

• Reading Text from Database

• Converting Text to Speech format

• Updating Database

Designing GUI for selecting keys

In this module user has to select some choice and he has to listen the voice of selected choice.

In this module we have to design GUI which provides buttons which provides various options like back,
0-9,and main menu button. .

Reading Text from Database

In this module, we have to connect to the database using JDBC API and fetch the text based on user
selected choice.
Converting Text to speech format

In this module, we are converting text format to speech format using Text to Speech API called tts API in
this module we are using predefined classes like VoiceManager , Voice ,etc which are exist in tts.jar file .

Updating Database

In this module admin can update database by adding new users and new select options related to college
environment.

2.5 Hardware And Software Requirements:

Hardware Interface:

We require speeker connection for interacting with voice. We use TCP/IP protocol for communicating
with local hosts. We also need system with P2 or above processor; 128MB+ RAM and database memory.

Software Interfaces

• Java, AWT, swings for designing GUI

• Java APIs like freeTTS for reading text and converting into speech

• Eclipse IDE for writing the programs.

• Operating System can be Windows XP, LINUX and Mac etc.

S-ar putea să vă placă și