ABSTRACT:

Voice User Interface (VUI) is the interface which works on the user’s demand in the form of speech. The speech engine recognizes the keyword from many ambiguous words in the surroundings and works on the user demand. The basic VUI is constructed by the XML Language.

The keyword has to be recorded in the speech engine at the time of construction. The basic security of the VUI is given by the confidentiality of the keyword for the specific work. The keyword refers to the password which is separate for each work that has to be performed by the system.

The new thing according to me is to make the system to understand our commands and work according to it with the same perfection. But the only difference is that we have not to store any keywords in the time of initialization.

The voice tester attached to the speech engine gives the security which tests the voice frequency of the user and allows only the authorized user to access the engine. This gave high security and which cannot be broken easily.

For that, have to include three different things in the library functions of the XML Language. The three things are:

1. User Language,
2. Translator,
3. Phonetics.

The user language is set according to the user and it should be included in the library function.

The user has option to give the command in different language and the translator converts it to the machine language.

The phonetics is the language of pronunciation. It includes all the pronunciations that have to be pronounced by the user. But the pronunciations by the user should be accurate.

The security of this VUI is high and it should be initialized. The user has to give the authorized voice that can only access the system. If the user wants to increase, the security, the voice modulation along with some keyword can also be stored in the system. This increases the security level in the system. The user can specify the no of users through that they can also be access the system with the specific key word.

The VUI has finds many applications in voice mailings, Home appliances, entertainment, etc.,

Kinect is the special device used to sense the voice of the user. The VUI finds its applications in cheaper and perfect manner. By, connecting this VUI to the speech engine to any of the appliances, we can make it as user-friendly.

By implementing, this concept in appliances and other systems, we can make our work simple, cheaper and quicker. The system connected with the speech engine is very helpful and is very easy to handle.

INTRODUCTION

Voice user Interface (VUI) is an interface which works on the demands of the user which are given in the form of speech.

VUI concept is firstly introduced to make some devices more secure. The voice can be a high secure element and which cannot be hacked easily by the user.

Also, it has main advantage of easy of work and saving the time of working the user has many demands and it can be easily done by the system.

Kinect is the speech device which is used to record the speech from the user and it converts it in to the words.

This device finds an application in the field of VUI to record the voice and send it to the system.

BASIC CONCEPT OF VUI

VUI has the basic concept of recording the voice and convert it to the words and works according to it. The following picture refers to the conversion of speech to words.

WORKING OF BASIC VUI

VUI which is basically word in some user- system interface in which the help of human is not required. For example, it can be used in the field of “Customer Care”, of the mobile companies.

Example

Consider a user calling to the customer care regarding the need of information

• The recorded voice of the system welcomes the user and gives the user, to choice and it explains the meaning of the choice.
• The user has to process a number according to his need and the system recognizes the number, and connects it to the respective module.

User: – //Calling for Customer Care//

Customer Care:- Welcome Sir,

Your choices are

1. Security code,
2. New Schemes,
3. Sim details
4. Balance enquiry

User: – //pressing no.2//

Customer Care: – Sir your choice is to know about the new schemes. The call is connected to our secretary.

//Now, the call is connected to the secretary//

• In this example the user has to specify a number and it is now processed and it gives details about it. Otherwise, if the demand is not solved by the system then it connects to the call to the Human who can clear all doubts of the user.

Draw backs:-

1. Pressing the number, is works of time
2. Suppose, our demand is in the choice 10 we have to wait until the 10^th choice appearance, It is waste of time.

IMPROVEMENT OF VUI

The VUI finds its improvement in the field of its applications. The applications have also improved along with the improvement of VUI.

There are three basic applications in this stage of VUI, they are

1. Customer Care,
2. Home appliance,
3. Mobile applications.

1. Customer Care:-
   • The improvement in this stage of VUI is in the saving of time the user has to specify his choice according to his demand instead of pressing the number.

Ex:

User: //calling for customer care//

Customer Care : Welcome Sir, your choices are

1. Security code

2. New schemes

3. Sim details

4. Balance enquiry

User: 2 //It is specified by speech//

Customer Care: Ok Sir, Now your call is connected to our chief.

• In this example, the user has to specify his choice through voice not by pressing the number.

Draw backs:-

1. Here also, the user has to wait by hearing all the choices until his choice appearance. It also wastes the time.

ii) HOME APPLIANCES:

• The VUI has found its application in the field of Home appliances. Here, the appliances work according to the user demand through voice.
• The vice keyword is to be different for different devices the keyword is to be specified at the time of initialization.

Ex:

1. If the user have to be on the Fan and off the fan. The keyword for this process is to be specified.

ON – F1

OFF- F2

Now, the user have to say “F1” if he wants to ON the fan, and he have to say “F2” if he wants to OFF the fan.

• Like that, he has to more the keyword for each appliance at the time of initialization.

Drawback:

1. The different key word for devices is difficult to have in the memory.
2. The security of keyword is only according to our confidential level.

iii) Mobile applications:-

• The VUI is used in come mobile applications. There is a mobile app which can react to our questions and it can be a companion to us.

Ex:-

User: Hay

App: Hay

User:what is your name?

App:My name is X

User:Do you like me?

App:Yes, I like you.

In this, example, the mobile interact with the user according to his question.

Draw backs:

The answer, given by the mobile is only stored in the form of templates. The reaction is similar for maximum number of questions by the user.

NEW CONCEPT ABOUT VUI:

My new idea about VUI is to make the system to understand the user’s demand and work according to it with the same perfection.

For that, the Library functions of XML language has to be included with some extra functions.

There are three main functions to be included in the Module: They are:

1. User Language,
2. Translator,
3. Phonetics

i) USER LANGUAGE:

The user can demand in any type of language which he can able to speak.

But only thing is that it is to be included in the Library functions. The user language should be a specific one. If we want to change the user language we have to say the keyword for changing to that language.

The keyword has to be specified at the time of initialization of the speech system.

ii) TRANSLATOR:

Translator can also be called as Convertor. Convertor has main work of converting the speech words into the words which can be understand by the system.

The speech engine records the speech in the form of speaking words and sent it to the computer in the form of words which can be understand by the computer.

This convertor is also included in the library functions of the XML. It does not require any keyword and it can be automatically executed.

iii) PHONETICS:

Phonetics is the representations of speaking words in the form of some special symbols which can also be included in the library functions.

It is very important in this case because this is to specify the pronunciation of words and it meaning.

The meaning of the word differs according to the pronunciation.

Ex: “read”

Is it present tense or past tense?

It is only depends upon the pronunciation of the word by the user.

The speech engine has to record the voice and it should by checked by the pronunciation and it is executed according to the meaning.

For placing a demand to the system, the user has to specify the correct pronouncing. Otherwise, the system responds to the meaning of the pronunciation.

Some of the applications to be implemented with VUI are:

1. CUSTOMER CARE:

• In this concept, it is very easy to select our choice in the customer care.
• The user has not to wait for the desired choice number. The user has to specify his need and system responds according to the demand.

Calling

Calling

Ex:User: //calling customer care//

Customer Care: Welcome Sir, What do you like to know sir?

User: About balance amount.

Customer Care: wait sir, we will send you the information of your balance via SMS, sir.

• Here, there is no job of waiting for the chief to solve the problem.

Advantage:

i) The user has not to wait for the choice to be heard. There is no waste to time.

2. Home appliances:

• The VUI has found its applications in Home appliances also. The keyword not necessary in the case of this concept.
• The system can understand our demand and respond to it accordingly.
• The statement given by the user may be different but the pronunciation and the competency must be accurate.Ex: If the user wants to ON the fan, there are many possibilities.

1. Switch on the fan (Or)
2. ON the fan, (or)
3. Turn on the fan

All the statements are accessed by the systems but the pronunciation matters.

3. MOBILE APPLICATIONS:

• The mobile app that respond to ourselves according to our questions and it cannot be a template function, if, we use this concept in VUI.
• The answers given by the mobile app is reasonable and it is a great companion to us.

4. VEHICLES:

• For example, a car can be started by a keyword stored by ourselves. The car can be started only if the voice is identified correctly and high security matters.
• The tape (or) FM in the car can be switch on by VUI and the channel of FM can be changed without any physical contact or eye contact and it does not destructs driving.

SECURITY:

The security of this VUI is only depends upon the voice modulation. The frequency of the voice of the user decides the ON/OFF of the device.

The frequency of the voice of user is stored in the system at the time of initialization. The system is accessed by only the authorized user.

For increasing the security. We can also include the passwords, and some special sounds that are only peculiar to ourselves can also be included.

The breaking of all these security is maximum impossible. Thus the system is prevented from Hacking.

CONCLUSION:-

By implementing this concept in the real-life applications, we can do our jobs faster, effective and secure.

By connecting this with the computer, we can make our computer as user-friendly.

By this, we can improve the security of the accessing of device and it enables the user to become smarter to do all the work in short span of time.