Content

____________________________________________________

1. Introduction ……………………………………………….. 02

2. Literature review ………………………………………… 04

3. Technologies ………………………………………………. 05

4. Design and methodology ……………………………. 06

5. Conclusion ………………………………………………….. 10

6. Reference …………………………………………………… 10

1|Page
1.Introduction
Upcoming trending technologies such as virtual reality, augmented
reality, voice interaction, IOT etc are changing the way people engage with the
world and transforming digital experiences. Voice control is one of important
development of human-machine interaction, which was possible because of
advancement in Artificial Intelligence. In current era, we are able to train our
machine to do their tasks by themselves or to think like humans using
technologies like Artificial Intelligence, Machine Learning, Neural Networks, etc.
we can talk to our machines with the help of virtual assistants. In recent time
great appearance of voice assistants such as Apple’s Siri, Google’s Assistant,
Microsoft’s Cortana and Amazon’s Alexa have been noticed due to heavy use of
smartphones. Voice assistants uses technologies like voice recognition, speech
synthesis, and Natural Language Processing (NLP) to provide various services
which help users to perform their task using their machine by just giving
commands in voice format and also with the help of Voice Assistant there will be
no need to write the commands again and again for performing particular task.
Virtual assistants are very useful for old generation people, people
with disabilities or special cases, small children who don’t know to operate
machines or smart gadgets, by making them sure that their interaction with
machine is not difficult anymore and also enable them to perform Multitasking.

1.1 Basics fundamental tasks performed by Voice assistants are as

follows:
 Search on web
 Play a music or video
 Setting a reminder and alarm
 Run any program or application
 Getting weather updates
 Sending WhatsApp, email messages etc.
2|Page
 These are very few examples of tasks performed by voice assistants, we
can do many more things according to our requirement. The capabilities and
improvements of voice assistants are continuously developing day by day to
provide better performance to users. We have used python modules and libraries
for making our Desktop based voice assistant so that our personal voice assistant
can run easily, smoothly on desktop.
The basic idea of our Project is that the user makes a request to voice
assistant through the Microphone of the device to get their work done and then
their command gets converted into text. Then the text request goes to processing
gives text response along with work done by voice assistant. Along with basic day
to day functionalities we are also trying to implement the concept of Face
detection for security purpose in our voice assistant to make it more flexible and
to it make it more personal. our program uses the least amount of system
resources which minimizes the expensive system requirements also reduces
threat to your system as it directly does not interact with servers.

1.2 Some Reasons why there is necessity of voice assistants:

There are lots of reason why this verbal voice command application is in
need in real time situations. Some of them are given below.
 To enable a highly engaging user experience:
Voice assistance engages users like no other interface. Users can
speak to the applications naturally to ask for whatever they'd like.

 To make application frustration free:

We have to touch, type and mouse in the existing machine system
to getting our work done, which are makes user frustrated sometimes. By
using voice assistant users can directly ask what they wanted to get done.

 To personalize your app experience for every user:

Voice assistants are actually able to respond for every user based
on their locality, language and preferences.

3|Page
  To Remove Language Barriers:
Voice Assistant technology are blended with Translation services
which helps users to handle them in their own language without
concerning about language barriers which allows them to interact more
freely with voice assistant.

2.Literature review
In today’s world we train our machine to think like humans and do their
task by themselves and what human being can do are being replaced by
machines. Based on this situation there comes concept of voice assistant capable
of completing various task for the humans based on their voice. Specific
commands given by the user to virtual assistant is capable of filtering out the
command and return relevant information [1].
People in the whole world are transforming their digital experience
using upcoming technologies like virtual reality, augmented reality, voice
interaction etc. Voice control is emerging as new evolution in Human and
Machine interaction where analog signal is converted by speech signal to digital
wave. In Last few years huge increase in the use of smart phones led to the great
use of voice assistant like Apple’s Siri, Google’s Assistant, Microsoft’s Cortana and
Amazon’s Alexa etc. Voice assistants are built using technologies like voice
recognition, speech synthesis, and Natural Language Processing (NLP) to provide
indefinite applications to the users to make their life easy and comfortable.

Voice assistants have several interesting services for their users such as:
● Answer to questions asked by users.
● Play music from streaming music services and Playing YouTube videos.
● Set timers or alarms.
● Send WhatsApp, email messages.
● Provide information about the weather.

4|Page
● Control other smart devices (lights, locks, thermostats, vacuum cleaners,
switches).

The capabilities of voice assistants are continuously extending according to the

users need [2].
According to Deepak Shende, Ria Umabiya, the AIVA (Microsoft, Google
Assistant from Google, and the recently appeared intelligent assistant under the
name "AIVA" 2018) aimed at developing a voice-controlled personal assistant
which is doing many things such as to search the Internet. It has some new
features like posting comments on the social media websites such as Facebook,
Twitter, etc. By just few simple commands. You can also know the weather
around you and can get the climate conditions in your region [3].
Tulshan explained that because of continuous typing there may be
possibility of injuries to the fingers of the user. To avoid such problems, we need
to design a system in which we can get our work done through our voice
commands. The voice will be recognized by the system and that recognized words
will be synthesized and if they are appropriate or makes some sense then that will
be printed on screen and after this again by recognizing the specific keywords the
program will be compiled and executed [4].
Dr. Kshama V. Kulhalli presented that survey between the top most voice
assistants like Google assistant, Apple’s Siri and Microsoft’s Cortana. Through this
survey it was concluded that Google assistant answers most accurate than others.
They could understand the variations in the voice very easily [5].

3.Technologies used:
 Python:
 Python is an interpreted high-level general-purpose programming
language.
 The version python 3.6.0 is used in the development of voice assistance
project.

5|Page
  PyCharm:
 PyCharm is the most popular IDE for Python
 It includes great features such as excellent code completion and
inspection with advanced debugger and support for web programming
and various frameworks.

4.Design and Methodology:

4.1 Existing System
In existing system, the audio command is taken as input through
microphone of the device. The next task of voice assistant will be to analyze audio
command and give appropriate output to the user.
The working process of existing system is shown below:

fig. processing in existing system

6|Page
4.2 Data flow diagram (DFD):
DFD is graphical representation of system which give detail
information about data flow between input and output. As level increases it
elaborates detail information about data flow.

4.2.1 DFD (level 0):

fig. data flow diagram (level 0)

7|Page
4.2.1 DFD (level 1):

fig. data flow diagram (level 1)

4.3 Packages used:

 Speech Recognition:
Speech Recognition library is used for listening to the words
spoken by the users that is taken as input from microphone as a source and
then process it for finding out its meaning and convert them into text
format. This library allows machine system to understand the human
language.

 Pyttsx3:
Pyttsx3 stands for Python text to speech library is used for making
our voice assistant talk to us. It supports common text to speech engines
which is like a tool that converts text into speech and makes voice assistant
able to talk to its user. We can make it talking in both male and female
voices according to requirement.

 Wikipedia:

8|Page
 We need to use Wikipedia library so that we can get information
from Wikipedia on any topic or we can also ask for solution to our query or
simply we can perform Wikipedia search for any topic using this library.
This Library in python needs Internet connection for fetching results and it
will provide results to user in text as well as voice format.

 Datetime:
This is an essential module to support the functionality of Date and
time. Whenever user wants to know the current date and time or the user
wants to schedule a task at a certain time then this module will be helpful
to them.

 PyAutoGUI:
PyAutoGUI is a Python Package which has control over the mouse
and the keyboard it is able to simulate the mouse cursor moves as well as
clicks the button press. With the help of particular 2-D coordinate we can
click on exact location on screen.

 PyWhatkit:
PyWhatKit is a Python Library which has number of features like
Sending messages, images through WhatsApp, playing YouTube videos,
converting image to ASCII, sending emails etc.

 Keyboard:
Keyboard is library in Python which provides user the full control
over the Keyboard. Especially the ‘press ()’ and ‘write ()’ function helps for
controlling keyboard keys as well as writing messages on screen.

 SpeedTest:
Speedtest library is essential to test internet bandwidth. It helps to
evaluate the uploading as well as downloading speed of Internet. All the
result that we get are in Megabits.

 OS:

9|Page
 OS (Operating System) module in Python is used for interacting with
operating system. Particularly we are using the ‘Start file ()’ to open any
application that are installed in our system.

These are some of the modules used for making voice assistant that can
perform very common features.

5.Conclusion:
In this Paper we have discussed uses, methodology as well as
implementation details of the personal Desktop based voice assistant using
Python which is built using open-source software PyCharm as an implementation
tool. This Project will be helpful for people of all generations as well as to people
with some disabilities or people with some special cases. The personal voice
assistant will be easy to use and will reduce the manual human efforts for
performing various tasks. The functionality of the current voice assistant system is
limited to working on Desktop based and working online (required to have
internet connection to perform tasks) only. The voice assistant system is modular
in nature so that addition of new features is possible without disturbing current
system functionalities.

6.Reference:

10 | P a g e