Voice Assistant- ‘Jarvisa’

1. SYNOPSIS

Project Title: Virtual Voice Assistant

Internal Guide: Prof. Dumbre S.A

Technical Keywords: Python Programming language, Artificial Intelligence, Microphone,

Speech Recognition, PyAudio.

1.1 Relevant Objectives:

A voice assistant is a digital assistant that uses voice recognition, language processing
algorithms, and voice synthesis to listen to specific voice commands and return relevant
information or perform specific functions as requested by the user.

In this ever-evolving digital world where speed, efficiency, and convenience are constantly
being optimized, it’s clear that we are moving towards less screen interaction. Virtual
assistants can tremendously save your time. Hence the main advantage of this voice search is
rapidity. Hence this idea is specially designed for Students Even the Simple tasks which we
handle manually can be handled easily.

The following are the major aims of this project:

1. Taking the input as speech patterns through the microphone.
2. To understand the flexibility of Virtual assistants.
3. Comparing the input with predefined commands.
4. Giving the desired output

1.2 Motivation:
A virtual assistant is an Artificial Intelligence technique. Voice assistants are changing the
way we use technology and the way we live. They have drastically improved over the last
five years and are finally available for every application. Voice assistants engage users like
no other interface. Users can speak to the applications naturally to ask for whatever they’d
like and can do so while multitasking. This also reduces the cognitive effort of the user.
Automating repeated tasks to a voice-activated personal assistant frees up human time and
resources.

Also, it can efficiently perform these mundane tasks with no errors, which often leads to an
improvement in customer satisfaction. While voice assistants are left
1
 Voice Assistant- ‘Jarvisa’

to deal with routine tasks, humans can dedicate more time to duties where human
intervention is required for successful business solutions and services

1.3 Hypothesis
Voice assistants are programs on digital devices that listen and respond to verbal commands.
A user can say, “What’s the weather?” and the voice assistant will answer with the weather
report for that day and location.
Users also task virtual assistants to make and receive phone calls, create text messages, get
directions, hear news and weather reports, find hotels or restaurants, check flight reservations,
hear music, or play games.
We have to just give commands and it can perform further functionalities.

 Hardware Requirements  Software requirements

1. Laptop Computer 1. Operating System: Windows 11

- Processor intel core i5 2. IDE: Visual Studio code
- Ram: 8GB

1.4 Requirement Specifications

1.5 Plan Of Project Execution

Figure shows the Gantt chart of various activities against a time scale in a weekly
manner.

2
 Voice Assistant- ‘Jarvisa’

Work Task Description Duration

Basic Study Related work done for 3weeks
Compendium
Review of papers Analysis of different techniques 3weeks
used in text summarization

Problem Formulation Critical analysis and results 2weeks

Achieved in research
Literature Survey Comparison of technology 3weeks
Studied
And result analysis
Objective of Topic Find some objectives related to 2weeks
system
Design of Mathematical Model Set theory and mathematics re 2weeks
Quired while designing the
system
Software requirement installation and understanding of 2weeks
And Specification software required for execution
of new system

Detailed Design Documents UML diagram and System 2weeks

Structure
Implementation of base GUI coding and first module 4weeks
paper
Selection of dataset Dataset Searching and Creation 2weeks
Implementation of proposed System Implementation of Module2 and 2weeks
module3
Testing of system Test system quality,fix errors if 2weeks
any
And improve if needed.Test
system for different datasets
Report writing Prepare initial report 2weeks
Final report with modification Prepare and modify the initial 1week
report
Following table summarises the activities carried out in each week cooresponding to the
gantt chart

3
 Voice Assistant- ‘Jarvisa’

2. INTRODUCTION

2.1 PROJECT IDEA

In today’s era almost all tasks are digitalized. We have Smartphone in hands
and it is nothing less than having world at your finger tips. These days we aren’t even
using fingers. We just speak of the task and it is done. There exist systems where we
can say Text Dad, “I’ll be late today.” And the text is sent. That is the task of a Voice
Assistant. It also supports specialized task such as booking a flight, or finding
cheapest book online from various ecommerce sites and then providing an interface
to book an order are helping automate search, discovery and online order operations.

Voice Assistants are software programs that help you ease your day to day
tasks, such as showing weather report, creating reminders, making shopping lists etc.
They can take commands via text (online chat bots) or by voice. Voice based
intelligent assistants need an invoking word or wake word to activate the listener,
followed by the command.. We have so many voice assistants, such as Apple’s Siri,
Amazon’s Alexa and Microsoft’s Cortana., Likewise we have built an assistant
named ‘JARVISA’.

This system is designed to be used efficiently on desktops. Personal assistant

software improves user productivity by managing routine tasks of the user and by
providing information from online sources to the user. JARVISA is effortless to use.
Just Give relevant commands through voice And within seconds, it gets executed.

This project was started on the premise that there is sufficient amount of
openly available data and information on the web that can be utilized to build a voice
assistant that has access to making intelligent decisions for routine user activities.

4
 Voice Assistant- ‘Jarvisa’

1.2 MOTIVATIONAL SURVEY

A voice assistant makes our life easier & helps users with functions that are the backbone of
our day. Someone who talks with you when you are alone or feel lonely someone who
manages your daily routines and takes care of your mental & physical health. The main
motivation is the voice assistant helps adults & disables people perform their day-to-day
tasks.

If we look at the daily life of a PC user, there are many tasks that must be automated instead
of wasting time doing them manually. Hence voice assistants can move out to handle such
operations eg., Managing notifications, Texting someone, web searching, etc.

1.3 LITERATURE SURVEY

There have been some significant advancements or innovations in the field of virtual
assistants with speech recognition. This is primarily due to its popularity in devices such as
smartwatches or fitness bands, speakers, Bluetooth, earphones, mobile phones, laptops or
desktop computers, televisions, and so on. Almost all digital devices on the market today
include voice assistants that allow users to control the device solely through speech
recognition. A new set of techniques is constantly being developed to improve the
performance of a voice-automated search. Each developer of a voice assistant uses its
specific methods and techniques for developing the system, consecutively which influences
the system. Оne аssistаnt саn synthesize sрeeсh mоre quаlitаtively, аnоther саn mоre
ассurаtely аnd withоut аdditiоnаl exрlаnаtiоns аnd соrreсtiоns рerfоrm tаsks,оthers аre
аble tо рerfоrm а nаrrоwer rаnge оf tаsks, but mоst ассurаtely аnd as the user wants..
Sinсe аll systems аre bаsed оn mасhine leаrning methоds аnd use fоr their сreаtiоn
huge аmоunts оf dаtа соlleсted frоm vаriоus sоurсes аnd then trаined оn them, аn
imроrtаnt rоle is рlаyed by the sоurсe оf this dаtа, be it seаrсh systems, vаriоus
infоrmаtiоn sоurсes оr sосiаl netwоrks. The аmоunt оf infоrmаtiоn frоm different sоurсes
determines the nаture оf the аssistаnt, whiсh саn result аs а result. Desрite the
different аррrоасhes tо leаrning, different аlgоrithms аnd teсhniques, the рrinсiрle оf
building suсh systems remаins аррrоximаtely the sаme.

5
 Voice Assistant- ‘Jarvisa’

2. PROBLEM DEFINATION & SCOPE

3.1 PROBLEM DEFINATION

Voice assistant should be able to model complex task dependencies and use these models
to recommend optimized plans for the user. It needs to be tested for finding optimum paths
when a task has multiple sub-tasks and each sub-task can have its own sub-tasks. In such a
case there can be multiple solutions to paths, and the it should be able to consider user
preferences, other active tasks, and priorities in order to recommend a particular.

A user may have a privacy concern as personal assistants require a huge amount of data
and are always listening to take the command This passive data is then, retained and shifted
through humans that are employed by almost all of the major companies- Amazon, Apple
etc. In addition to this discovery over the Ai being able to record our audio interactions,
there have been concerns over the type of data such employees and contractors were
hearing. So, in the cloud-based voice assistant, a privacy policy must be there that will
protect the user information. Jarvisa removes all the privacy issues in voice Assistant
ecosystems.

3.2 SCOPE
Voice search has been a hot topic of discussion. Visibility of voice will undoubtedly be a
challenge. This is because the visual interface with voice assistants is missing. Users simply
cannot see or touch a voice interface unless it is connected to the Alexa or Google Assistant
app. Search behaviors, in turn, will see a big change voice assistants will continue to offer
more individualized experiences as they get better at differentiating between voices.

However, it’s not just developers that need to address the complexity of developing for voice
as brands also need to understand the capabilities of each device and integration and if it
makes sense for their specific brand. They will also need to focus on maintaining a user
experience that is consistent within the coming years as complexity becomes more of a
concern. This is because the visual interface with voice assistants is missing. Users simply
cannot see or touch a voice interface

6
 Voice Assistant- ‘Jarvisa’

4. OBJECTIVES & FEATURES

4.1 OBJECTIVES
The main objective of building personal assistant software (a virtual assistant) is using
semantic data sources available on the web, user-generated content, and providing knowledge
from knowledge databases.

The main purpose of an intelligent virtual assistant is to answer questions that users may
have. This may be done in a business environment, for example, on a business website, with a
chat interface. On the mobile platform, the intelligent virtual assistant is available as a call-
button-operated service where a voice asks the user “What can I do for you?” and then
responds to verbal input

As said earlier available assistants in the market today lack privacy. All the assistants provide
our data to the respective companies who have made them. like Apples Siri, Amazons Alexa,
etc. Violations of privacy id prevented when you built your own assistant and this is what we
have carried out in our project.

Feasibility Study

Feasibility study can help you determine whether or not you should proceed with

your project. It is essential to evaluate cost and benefit. It is essential to evaluate cost
and benefit of the proposed system. Five types of feasibility study are taken into
consideration.

 Technical feasibility:

 It includes finding out technologies for the project, both hardware and software. For virtual
assistant, user must have a microphone to convey their message and a speaker to listen when
system speaks. These are very cheap now adays and everyone generally possess them.

7
 Voice Assistant- ‘Jarvisa’

Besidesthe , system needs internet cone ction.While using JARVISA, make sure you have a
steady internet connection.

 Operational feasibility:

 It is the ease and simplicity of operation of the proposed system. System does not require any
special skill set for users to operate it. In fact, it is designed to be used by almost everyone.
Kids who still don’t know to write can readout problems for system and get answers.

 Economical feasibility:

 Here, we find the total cost and benefit of the proposed system over current system. For this
project, the main cost is documentation cost. User also would have to pay for microphone and
speakers. Again, they are cheap and available. As far as maintenance is concerned, JIA won’t
cost too much.

8
 Voice Assistant- ‘Jarvisa’

4.2 Features Supported by Jarvisa

Following are the features supported by the assistant for desktop:-

 Basic features

 Handle System tasks(like managing windows, widgets, launch settings, notifications,

etc.)
 Can search user commands on Google
 Tell Location
 Tell Weather
 Tell the Date and Time
 Take Screenshots
 Can play music, Audio, and videos.
 Open news
 Voice Input
 Shutdown, restart PC

 Youtube Automation

 Youtube Search
 Playing Videos Automatically
 Handling operations of videos like Playing, pausing, muting etc
 Changing Different Modes(like filmy mode,full screen mode,default mode)

 Browser Automation & Searching

• Opening browser
• Closing/opening a new tab
9
 Voice Assistant- ‘Jarvisa’

• Open all websites

• Opening History
• Opening Downloaded content
• Saving the website
• Bookmarking a website
• Automatically generating a pdf
• Wikipedia search

5. METHODOLOGY

 ABOUT PROGRAMMING LANGUAGE

This project is developed using Python programming language.

Python is a high-level, general-purpose programming language. Its design philosophy

emphasizes code readability with the use of significant indentation via the off-side rule.

Python's large standard library provides tools suited to many tasks and is commonly cited as
one of its greatest strengths. For Internet-facing applications, many standard formats and
protocols such as MIME and HTTP are supported. It includes modules for creating graphical
user interfaces, connecting to relational databases, generating pseudorandom numbers,
arithmetic with arbitrary-precision decimals, manipulating regular expressions, and unit
testing.

Python is commonly used in artificial intelligence projects and machine learning projects
with the help of libraries like TensorFlow, Keras, PyTorch, and sci-kit-learning. As a
scripting language with a modular architecture, simple syntax, and rich text processing tools,
Python is often used for natural language processing.

 ABOUT THE DEVELOPMENT ENVIRONMENT

An IDE provides a smooth working environment for any development project For this project
we have used Visual Studio Code.

Visual Studio Code is a streamlined code editor with support for development operations
like debugging, task running, and version control. It aims to provide just the tools a developer

10
 Voice Assistant- ‘Jarvisa’

needs for a quick code-build-debug cycle and leaves more complex workflows to fuller
featured IDEs, such as Visual Studio IDE.

Working with Python in Visual Studio Code, using the Microsoft Python extension, is simple,
fun, and productive. The extension makes VS Code an excellent Python editor and works on
any operating system with a variety of Python interpreters. It leverages all of VS Code's
power to provide auto-complete and IntelliSense, linting, debugging, and unit testing, along
with the ability to easily switch between Python environments, including virtual
environments

5.2 PYTHON MODULES REQUIRED:

1)Pyttsx3

Pyttsx 3 is a text-to-speech conversion library in Python. Unlike alternative libraries, it

works offline and is compatible with both Python 2 and 3… It is a very easy-to-use tool that
converts the entered text into speech..It supports three TTS engines :

- Sapi5 – SAPI5 on Windows

- Nsss – NSSpeechSynthesizer on Mac OS

- X Espeak – eSpeak on every other platform

2) Os module

The OS module in Python provides functions for interacting with the operating system.
OS comes under Python’s standard utility modules. This module provides a portable way of
using operating system-dependent functionality.

3)Wikipedia module

Wikipedia is a library in Python which it possible for the virtual assistant to process
queries regarding. This is an online library and needs an internet connection to fetch the
results. The no. of lines that the user wants to get as a result can be set manually

4)datetime module

A module named datetime can be imported to work with the date as well as time. Python
datetime module comes built into Python, so there is no need to install it externally.. Date and
11
 Voice Assistant- ‘Jarvisa’

datetime are an object in python, so when you manipulate them, you are actually
manipulating objects and not string or timestamps.

5) webbrowser

The webbrowser module provides a high-level interface to allow displaying web-based

documents to users. Under most circumstances, simply calling the open() function from this
module will do the right thing.

6) Beautiful soup

Beautiful Soup is a Python library for pulling data out of HTML and XML files. It works
with your favorite parser to provide idiomatic ways of navigating, searching, and modifying
the parse tree. It commonly saves programmers hours or days of work.

7) pywhatkit

Get information on a particular topic. Play a YouTube video,Perform a Google Search.

In Python3 pywhatkit module will not come pre-installed, so you can install it from web.

8) Request module

Requests is an HTTP library for the Python programming language. The goal of the project is
to make HTTP requests simpler and more human-friendly. 

9)Keyboard module

Take full control of your keyboard with this small Python library. Hook global events,
register hotkeys, simulate key presses, and much more.

12
 Voice Assistant- ‘Jarvisa’

5.1 WORKING :

Communicating with a voice assistant is so simple it almost makes us forget how impressive
the technology behind it is. 

1. If you’ve ever used a voice assistant on your phone, then you know that it first needs
a keyword that activates it, like ‘OK, Google’. When you pose a question or give
a command to your voice assistant it is converted thanks to the use of Automatic Speech
Recognition (ASR), which enables the device to recognize and translate it from speech to
text. 

13
 Voice Assistant- ‘Jarvisa’

2. After that comes text interpretation: thanks to Natural Language Processing (NLP), the
machine can identify the intent behind what you said, the meaning of the words as well as
context.

3. Now that the machine knows what was said and (presumably) what your intention was, it
can search for a valid answer, and respond accordingly. The response is converted from
written to spoken form using a text-to-speech (TTS) technology, and voila: your voice
assistant speaks. All done in a matter of seconds

6. SYSTEM DESIGN AND SPECIFICATIONS

6.1 System Architecture

The proposed model of the voice assistant is as shown in the above figure 1. The model
consists of user input through microphone to accept commands from the user. These
commands are then go through Speech Recognition, it is the ability of a machine or program
to identify words and phrases in spoken languages and convert them to a machine-readable
format. On these input Natural Language Processing is applied, it is a field which is created
by amalgamating computer science and artificial intelligence. Using NLP, we are concerned
14
 Voice Assistant- ‘Jarvisa’

with interactions between computers and human natural languages. Then the BRAIN check
whether it is a question or an action, if it is a action than the action is performed by the voice
assistant and acknowledgment is given to the user via a synthesis voice or if it is a question
than it is search in dialog box or knowledge base and then response via a synthesis voice to
the user. Our Voice assistant uses google text-to-speech API to understand all the words
spoken by the user, and based on certain conditions that satisfy being a command the voice
assistant sends responses to the user.

5.3 FLOWCHART

15
 Voice Assistant- ‘Jarvisa’

Initially, the system is in idle mode. As it receives any wake up call it begins execution.
The received command is identified whether it is a questionnaire or a task to be performed.
Specific action is taken accordingly. After the Question is being answered or the task is being
performed, the system waits for another command. This loop continues unless it receives quit
command. At that moment, it goes back to sleep

5.4 ENTITY-RELRATIONSHIP DIAGRAM

16
 Voice Assistant- ‘Jarvisa’

The above diagram shows entities and their relationship for a voice assistant
system. We have a user who will give commands through voice. The user here is
an entity.

We have other four entities here i.e, web search, youtube automation and browser
automation,system and settings. Each entities have their own attributes.
Single user can ask multiple questions. Each question will be given ID to get
recognized along with the query and its corresponding answer. User can also be
having n number of tasks. These should have their own unique id and status i.e.
their current state. A task
should also have a priority
value and its category
whether it is a parent
task or child task of an older
task.

5.5 Data Flow Diagrams

DFD Level 0:

Level 0 of dfd gives overview components of a system. The user sends request to assistant
and thereby gets response as per given command.

17
 Voice Assistant- ‘Jarvisa’

DFD Level 01:

Level 1 still gives a a general overview of the system it gives the complwtw flow of
recognizing voice commands, searching for output at python back end and finally the Text-
to-speech conversion response to user.

DFD Level 02:

Level 02 of Dfd gives detailed workflow of system.It shows the switching job of assistant to
various functionalities as required. Finally the response data is converted to speech

18
 Voice Assistant- ‘Jarvisa’

5.6 Use Case Diagram

1. PERFORMANCE EVALUATION AND TESTING

Type of testing mechanism

carried out:
Out of the available testing
mechanism,i.e, Automation testing
and manual testing we have carried out
manual testing. By following certain
testing methodologies and test cases.Each
test case is evaluated and result is noted.
For an AI-based voice assistant ecosystem,
it’s necessary to check whether it performs
the desired tasks successfully,capable

19
 Voice Assistant- ‘Jarvisa’

of voice recognition, its response time, etc.h ence different tests are performed to checks its
individual and integrated functionalities.

6.1 Testing Methodologies

A strategy for software testing must accommodate low-level tests that are necessary to verify
that a small source code segment has been correctly implemented as well as high-level tests
that validate major system functions against customer requirements A strategy must provide
guidance for the practitioner and a set of milestones for the manager. Because the steps of the
test strategy occur at a time when deadline pressure begins to rise, progress must be
measurable and problems must surface as early as possible. Following testing techniques are
well known and the same strategy is adopted during this project testing.

6.1.1 Unit Testing

Unit testing focuses verification effort on the smallest unit of software design- the software
componentor module. The unit test is white-box oriented. The unit testing implemented in
every module of Voice Assistant System, by given correct manual input to the system, the
data is analyzed through the code and retrieved. If you want required module to access input
or gets the output from the End user. Any error will accrued the time will provide handler to
show what type of error will accrued.

6.1.2 System Testing

System testing is actually a series of different tests whose primary purpose is to silly exercise
the computer-based system. Below we have described the two types of testing which have
been taken for this project it is to check all modules worked on input bases if you want
change any values or inputs will change all information. So specified impoit is must

6.1.3 Performance testing

Performance testing is designed to test the run-time performance of software within the
context of an integrated system Usability Performance Testing makes sure that the AI
components of the app are working correctly. It is targeted to Product Managers and developers.
20
 Voice Assistant- ‘Jarvisa’

The main goal is to identify issues with the speech recognition and Natural Language
Understanding behavior of the assistant and your app. It consists of comprehensive testing of the
interaction model, creating a baseline set of results. These results, in turn, are the basis for making
improvements to the interaction model and the code of the skill – once revisions are completed,
additional tests are run to ensure everything is working as expected.

6.2 TEST CASES

Test Title: Response Time

Test ID: T1

Test Priority: High

Test Objective: To make sure that the system response time is efficient.

Description:

21
 Voice Assistant- ‘Jarvisa’

Time is very critical in a voice-based system. As we are not typing inputs, we are speaking
them. The system must also reply within seconds, User must get an instant reply to a given
query. However, in this system response time depends on the speed of the internet
connection.

Expected result: Should reponse within seconds

Actual result: Responses within seconds.

Test status: Passed

Test Title: Accuracy

Test ID: T2

Test Priority: High

Test Objective: To assure that answers retrieved by the system are accurate as per gathered
data. Description: A virtual assistant system is mainly used to get precise answers to any
question asked. Getting an answer in a moment is of no use if the answer is not correct.
Accuracy is of utmost importance in a virtual assistant system. It should accurately complete
any task or answer any question asked by the user

Expected result: Should provide accurate answers

Actual result: Provides the accurate answers

Test status: Passed

Test Title: Approximation

Test ID: t3

Test priority: Moderate

Test Objective: To check approximate answers in response.

Description:

There are times when, we ask the assistant to make a google search, youtube search, etc.
22
 Voice Assistant- ‘Jarvisa’

At this point approximation in answering is required, Both while listening and during text-to-
speech conversion. This is because our assistant is on a based o voice search mechanism.
Getting exact values in such cases is undesirable

Expected result: It should make proper speech recognition and text-to-speech comversion

Actual result: makes proper speech recognition and answers perfectly

Test status: Passed

Test Title: Response to Web search

Test ID: t4

Test priority: Moderate

Test Objective: To check approximate answers is obtained through web.

Description:

The Assistant Should be able to access web pages and perform all the browser automation
like opening a new tab, closing tabs, opening web history, etc. However, the query will be
answered based on the speed of the internet connection.

Expected result: It should give relevant responses for web search

Actual result:Gives relevant responses for web search

Test status: Passed

Test Title: Response to video/Youtube search

Test ID: t5

Test priority: Moderate

Test Objective:

Description:

23
 Voice Assistant- ‘Jarvisa’

The Assistant Should be able to access Online youtube videos. Also, it should be able to
access Local pc videos. It should perform all the video automation features like playing the
video, pausing it ,muting it, changing the modes of the screen etc.

Expected result: It should give relevant responses for Youtube and videos.

Actual result: Gives relevant responses for Youtube and videos

Test status: Passed

Test Title: Response to System Automation

Test ID: 6

Test priority: Moderate

Test Objective: To check if assistant performs given system functionalities

Description:

The Assistant Should be able to Perform system automation features. These features include
Launching settings,dealing with windows manager,opening widgets, date and time,etc.Also,
it should be able to access Local pc videos. It should perform all the video automation
features like playing the video, pausing it ,muting it, changing the modes of the screen etc.

Expected result: It should give relevant responses for System Automation

Actual result: Gives relevant responses for System Automation .

Test status:Passed

Test Title: Real time testing

Test ID: 6

Test priority: Moderate

Test Objective: To check if assistant performs given real time functionalities.

Description:
24
 Voice Assistant- ‘Jarvisa’

The Assistant Should be able to Perform all the real time functionalities. These features
include location search,etc .It should open google maps on commanding.

Expected result: It should give relevant responses for location search.

Actual result: Gives relevant responses for Location search.

Test status:Passed

2. RESULT ANALYSIS

7.1 OUTPUT
25
 Voice Assistant- ‘Jarvisa’

The following pictures show the resulting jobs done when we ask our assistant to do any

• Opening Notifications

In the Output given below Jarvisa opens notifications You just have to command “Show
Notifications”, and it will prompt u the notification box.

Showing weather
Similarly, it will show weather When u’ll ask “What’s the Weather?”

26
 Voice Assistant- ‘Jarvisa’

• Showing widgets

• Showing window manager layouts:

It will open widgets on commanding as “Open widgets”and also the windows manager
layouts when we say “Windows Manager” in command

27
 Voice Assistant- ‘Jarvisa’

• Opening Settings

Logging out from pc

28
 Voice Assistant- ‘Jarvisa’

 Youtube Automation

Includes playing pausing,muting operations on youtube videos following is the output

screen

 Loading video

 Shifting to Cinema mode

29
 Voice Assistant- ‘Jarvisa’

 Browser Automation

 Opening website

• Searching location

30
 Voice Assistant- ‘Jarvisa’

7.1 CONCLUSION
Through this voice assistant, we have automated various services using a single
line command. It eases most of the tasks of the user like searching the web,
retrieving weather forecast details, vocabulary help and medical related
queries. We aim to make this project a complete server assistant and make it
smart enough to act as a replacement for a general server administration. The
future plans include integrating David with mobile using React Native to
provide a synchronised experience between the two connected devices.
Further, in the long run, David is planned to feature auto deployment
supporting elastic beanstalk, backup files, and all operations which a general
Server Administrator does. The functionality would be seamless enough to
replace the Server Administrator with David.

7.2 FUTURE WORK

The virtual assistants which are currently available are fast and responsive but we still have to
go a long way. The understanding and reliability of the current systems need to be improved a
lot. The assistants available nowadays are still not reliable in critical scenarios. The future of
these assistants will have the virtual assistants incorporated with Artificial Intelligence which
includes Machine Learning, Neural Networks, etc. and IoT. With the incorporation of these
technologies, we will be able to achieve new heights. What the virtual assistants can achieve
is much beyond what we have achieved till now. Most of us have seen Jarvis, that is a virtual
assistant developed by iron man which is although fictional but this has set new standards of
what we can achieve using voice-activated virtual assistants

31
 Voice Assistant- ‘Jarvisa’

REFERENCES

1. Kaiming He, Xiangyu Zhang, Shaoqing Ren, and David Sun. Spatial pyramid pooling in
deep convolutional networks for visual recognition. In European Conference on Computer
Vision, pages 346–361. Springer,2014

2. M. F. Kader and K. Deb, “Neural network based English alphanumeric character

recognition”, International Journal of Computer Science, Engineering and
Applications (IJCSEA) Vol.2, No.4, August 2012.

3. Jyoti Dalal and Sumiran Daiya “Image Processing Based Optical Character Recognition
Using MATLAB” International Journal of Engineering Sciences & Research Technology,
ISSN: 2277-9655, CODEN: IJESS7, Dalal et al., 7(5): May 2018

4. Tan Chiang Wei, U. U. Sheikh, Ab Al-Hadi Ab Rahman. “Improved Optical Character

Recognition with Deep Neural Network”, 2018 IEEE 14th International Colloquium on
Signal Processing / its Applications (CSPA 2018), 9 -10 March 2018

5. https://www.geeksforgeeks.org/voice-assistant-using-python/

6. https://www.miquido.com/blog/what-are-voice-assistants/

7. https://www.academia.edu/40229169/
PROJECT_REPORT_ON_VIRTUAL_ASSISTANT_SUBMITTED_BY_NAAZNEEN_
JATU

8. Python-Complete Reference – by Martin C. Brown

32
Voice Assistant- ‘Jarvisa’

33
Voice Assistant- ‘Jarvisa’

34
Voice Assistant- ‘Jarvisa’

35
Voice Assistant- ‘Jarvisa’

36
Voice Assistant- ‘Jarvisa’

37
Voice Assistant- ‘Jarvisa’

II

38