Project Report GitHub

CONTENTS
Sl No Chapter Name Page No
1 Introduction 9
1.1 Introduction to Voice Assistants
1.2 Aim and Purpose
2 Literature survey 11
2.1 Survey on Virtual Assistant: Google Assistant,

Alexa, Siri, Cortana
2.2 Survey on Smart Virtual Voice Assistant
2.3 Survey on Personal Assistant
2.4 Survey on Personal Desktop Virtual Voice

Assistant Using Python
2.5 Smart Home Voice Assistants: A Literature Survey

of User Privacy and Security Vulnerabilities
3 Existing System 14
3.1 Overview of existing systems
3.2 Limitations of existing system
4 Proposed System 15
4.1 Introduction of proposed system
4.2 Features
4.3 System Architecture

CONTENTS
Sl No Chapter Name Page No
5 System Design 17
5.1 Requirement Analysis
5.2 Data Flow Diagram
5.3 ER Diagram
5.4 Use Case Diagram
6 Coding 22
7 Testing 28
7.1 Types of Testing
7.2 Test Results

8 Conclusion and Future Enhancement 35
9 Screenshots 36
10 References 39
List of Figures
Sl No Figure Name Page No

1 System Architecture 16
2 Level 0 data flow diagram 18
5 ER Diagram 20
6 Use Case Diagram 21

Virtual Voice Assistant
CHAPTER 1
INTRODUCTION
1.1 Introduction to Voice Assistants
Voice assistants are artificial intelligence (AI) systems that enable users to interact with
devices and perform tasks using natural language voice commands. Voice assistants have
become increasingly popular in recent years, with many people using them to control smart
devices, access information, and perform a variety of tasks on their smartphones, smart
speakers, and other devices.
Voice assistants use natural language processing (NLP) algorithms and machine learning
techniques to understand and respond to user requests. They can be activated using a
specific trigger word or phrase, such as "Hey Siri" or "Ok Google," and can perform a wide
range of tasks, such as answering questions, setting reminders, playing music, or controlling
smart home devices.
Voice assistants have the potential to make many everyday tasks more convenient and
efficient, as they allow users to interact with devices and systems using their voice rather
than requiring them to use a physical interface or input commands manually. However,
voice assistants also raise privacy and security concerns due to the sensitive personal data
that they may collect, store, and process.
Overall, voice assistants are an emerging and rapidly evolving technology that has the
potential to transform how people interact with devices and systems, and they will likely
continue to play an important role in the development of AI and the internet of things (IoT).
9
1.2 Aim and purpose
Purpose of virtual assistant is to being capable of voice interaction, music playback, making
to-do lists, setting alarms, streaming podcasts, playing audiobooks, and providing weather,
traffic, sports, and other real-time information, such as news. Virtual assistants enable users
to speak natural language voice commands in order to operate the device and its apps.
There is an increased overall awareness and a higher level of comfort demonstrated

specifically by millennial consumers. 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.
10
CHAPTER 2
LITERATURE SURVEY
2.1 Survey on Virtual Assistant: Google Assistant, Siri, Cortana, Alexa
Authors: Amrita S. Tulshan and Sudhir Namdeorao Dhage
Virtual assistant is boon for everyone in this new era of 21st century. It has paved way for a
new technology where we can ask questions to machine and can interact with IVAs as
people do with humans. This new technology attracted almost whole world in many ways
like smart phones, laptops, computers etc. Some of the signiﬁcant VPs are like Siri, Google
Assistant, Cortana, and Alexa. Voice recognition, contextual understanding and human
interaction are the issues which are not solved yet in this IVAs. So, to solve those issues100
users participated a survey for this research and shared their experiences. All users’ task was
to ask questions from the survey to all personal assistants and from their experiences this
research paper came up with the actual results. According to that results many services were
covered by these assistants but still there are some improvements required in voice
recognition, contextual under-standing and hand free interaction. After addressing these
improvements in IVAs will deﬁnitely increased its use is the main goal for this research
paper.
2.2 Survey On Smart Virtual Voice Assistant
Authors: Manjusha Jadhav, Krushna Kalyankar, Gnaesh Narkhede and Swapnil Kharose
In this modern era, day to day life became smarter & interlinked with technology. We
already know some voice assistant like Google, Siri etc. Now in our voice assistant system,
it can act as your smart friend, daily schedule manager, to do writer, calculator & search
tool. This project works on speech input & give output through speech & text on screen.
This assistant attaches with the world wide web to provid result that the user required.
Natural language processing algorithm helps machines to engage in communication using
natural human language in many forms.
11
2.3 Survey on Personal Voice Assistant
Authors: S. Lahari, A. Naveen, G. Sarath Chandra
Digitization brings new possibilities to ease our daily life activities by the means of assistive
technology. Amazon Alexa, Apple Siri, Microsoft Cortana, Samsung Bixby, to name only a
few were successful in the age of smart personal assistants (spas).A voice assistant is
defined a digital assistant that combines artificial intelligence, machine learning Speech
Recognition, Natural Language Processing (NLP), Speech Synthesis and various actuation
mechanisms to sense and influence the environment. We use different NLP techniques to
convert Speech to text (STT), then process the text, convert Text to Speech (TTS), add
various functionalities. However, SPA research seems to be highly fragmented among
different disciplines, such as computer science, human-computer-interaction and
information systems, which leads to ‘reinventing the wheel approaches’ and thus impede
progress and conceptual clarity. In this paper, we present an exhaustive, integrative literature
review to build a solid basis for future research. Hence, we contribute by providing a
consolidated, integrated view on prior research and lay the foundation for an SPA
classification scheme.
2.4 Survey on Personal Desktop Virtual Voice Assistant using Python
Authors: Prof. Suresh V. Reddy, Chandresh Chhari, Prajwal Wakde, Nikhil Kamble
In today’s develop generation, How cool is it to build your own personal assistants like
Alexa or Siri? It’s not very complex and may be effortlessly performed in Python. Personal
virtual assistants are capturing numerous attentions lately. Chat bots are not unusual in
maximum business web sites. The predominant agenda of our voice help makes human
beings clever and supply immediate and computed effects. The fundamental mission of a
voice assistant is to reduce using enter gadgets like keyboard, mouse, touch pens, and so
forth. This will lessen both the hardware fee and space taken by it.
12
2.5 Smart Home Voice Assistants: A Literature Survey of User Privacy and
Security Vulnerabilities
Authors: Prof. Suresh V. Reddy, Chandresh Chhari, Prajwal Wakde, Nikhil Kamble
Intelligent voice assistants are internet-connected devices, which listen to their environment
and react to spoken user commands in order to retrieve information from the internet,
control appliances in the household, or notify the user of incoming messages, reminders, and
the like. With their increasing ubiquity in smart homes, their application seems only limited
by the imagination of developers, who connect these off-the-shelf devices to existing apps,
online services, or appliances. However, since their inherent nature is to observe the user in
their home, their ubiquity also raises concern of security and user privacy. To justify the
trust placed into the devices, the devices must be secure from unauthorized access and the
back-end infrastructure tasked with speech-to-text analysis, command interpretation, and
connection to other services and appliances must maintain confidentiality of data. To
investigate existing possible vulnerabilities, approaches to mitigate them, as well as general
considerations in this emerging field, we supplement the findings of a recent study with
results from a systematic literature review. We were able to compile a list of six main types
of user privacy vulnerabilities, partially confirming previous findings, but also finding
additional issues. We discuss these vulnerabilities, their associated attack vectors, and
possible mitigations users can take to protect themselves.
13
CHAPTER 3
EXISTING SYSTEM
3.1 Overview of existing system
A virtual voice assistant is a software program that utilizes natural language processing and
voice recognition technologies to understand and respond to spoken commands and queries.
It allows users to interact with their devices, applications, and services using voice
commands, and can perform a wide range of tasks such as making phone calls, scheduling
appointments, setting reminders, and providing information. Some popular examples of
virtual voice assistants include Amazon Alexa, Google Assistant, and Apple Siri. These AI-
powered systems can be integrated with other devices and services to create a more seamless
and convenient user experience.
3.2 Disadvantages of existing system

1. Performance: Voice assistants may have limitations in terms of their performance,
such as the speed at which they can process and respond to user requests, or the
complexity of tasks that they can handle.
2. Privacy and security: Voice assistants may not always clearly communicate their
data collection and sharing practices to users, which could raise concerns about
transparency and consent.
3. Customization: Voice assistants may not offer users a high degree of customization
or control over their functionality, which could limit their usefulness and appeal to
users.
4. Accuracy: Voice assistants may not always accurately understand or respond to user
requests and queries, which can lead to frustration and a poor user experience.
5. Capabilities: Voice assistants may not support all tasks or functions that users may
want to perform, and they may not be able to integrate with all devices or systems.
14
CHAPTER 4
PROPOSED SYSTEM
4.1 Features
 It can get some real time information such as news headlines, weather report, IP
address, Internet speed, and system stats.
 It can also get entertaining contents such as jokes, latest movies or TV series, and
playing songs and videos in YouTube.
 It can also generate an image from given text and can also send an email.
 It can perform system operations such as opening/closing/switching tabs,

copying/pasting/deleting/selecting the text, creating a new file, taking screen shot,
minimizing/maximizing/switching/closing windows.
 It can also get brief information on any topic, perform arithmetic operations, and
answer any general knowledge question.
 It can perform google search, find map or distance between two places on google
maps.
 We can also get the chat history along with date & time of the query.
 It can also open any installed app and some websites, we can also take notes with
help of assistant.
4.2 Advantages of Proposed System
 It can create an image from the given text.
 Send email to specified mail id by dictating the message.
 It is free of cost.
 Modification can be done quickly and easily.
 It maintains privacy as user data is not shared with third parties.
15
4.3 System Architecture
Figure 4.4.1 System Architecture (Voice Assistant)
16
CHAPTER 5
SYSTEM DESIGN
5.1 Requirement Analysis
In order to effectively design and develop a system, it is important to understand and

document the requirements of the system. The process of gathering and documenting the
requirements of a system is known as requirement analysis. It helps to identify the goals of
the system, the stakeholders and the constraints within which the system will be developed.
The requirements serve as a blueprint for the development of the system and provide a
reference point for testing and validation.
 Hardware Requirements
o Processor – 2.3 GHz or more
o RAM – 4 GB or more
o Disk Space – 50 GB or more
o Input Devices – Microphone & Keyboard
o Output Devices – Speaker & Monitor
o Internet Connection
 Software Requirements
o Python 3.9 or later
o Python packages
• SpeechRecognition==3.8.1
• tensorflow==2.10.0
• Keras==2.10.0
• scikit-learn==1.1.2
o APIs
• News API
• WolframAlpha API
• OpenWeatherMap API
• TMDB API
• DreamStudio API
17
5.2 Data Flow Diagram
 Level 0 data flow diagram
Figure 5.2.1 Level 0 Data Flow Diagram
18
19
5.3 ER Diagram
Figure 5.3.1 ER Diagram (Voice Assistant)
20
5.4 Use Case Diagram
Figure 5.4.1 Use Case Diagram (Voice Assistant)
21
CHAPTER 6
CODING
main.py
try:
# importing prebuilt modules
import os
import logging
import pyttsx3
logging.disable(logging.WARNING)
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3' # disabling warnings
for gpu requirements
from keras_preprocessing.sequence import pad_sequences
import numpy as np
from keras.models import load_model
from pickle import load
import speech_recognition as sr
import sys
sys.path.insert(0, os.path.expanduser('~') +
"/PycharmProjects/Virtual_Voice_Assistant")
# sys.path.insert(0,
os.path.expanduser('~')+"/Virtual_Voice_Assistant") # adding voice
assistant directory to system path
# importing modules made for assistant
from database import *
from image_generation import generate_image
from gmail import send_email
from API_functionalities import *
from system_operations import *
from browsing_functionalities import *
except (ImportError, SystemError, Exception, KeyboardInterrupt) as
e:
print("ERROR OCCURRED WHILE IMPORTING THE MODULES")
exit(0)
recognizer = sr.Recognizer()
engine = pyttsx3.init()
engine.setProperty('rate', 185)
sys_ops = SystemTasks()
tab_ops = TabOpt()
win_ops = WindowOpt()
# load trained model
22
model = load_model('..\\Data\\chat_model')
# load tokenizer object

with open('..\\Data\\tokenizer.pickle', 'rb') as handle:
tokenizer = load(handle)
# load label encoder object

with open('..\\Data\\label_encoder.pickle', 'rb') as enc:
lbl_encoder = load(enc)
def speak(text):
print("ASSISTANT -> " + text)
try:
engine.say(text)
engine.runAndWait()
except KeyboardInterrupt or RuntimeError:
return
def chat(text):
# parameters
max_len = 20
while True:
result =
model.predict(pad_sequences(tokenizer.texts_to_sequences([text]),
truncating='post', maxlen=max_len), verbose=False)

intent =
lbl_encoder.inverse_transform([np.argmax(result)])[0]
return intent
def record():
with sr.Microphone() as mic:
recognizer.adjust_for_ambient_noise(mic)
recognizer.dynamic_energy_threshold = True
print("Listening...")
audio = recognizer.listen(mic)
try:
text = recognizer.recognize_google(audio,
language='us-in').lower()
except:
return None
print("USER -> " + text)
return text
def listen_audio():
try:
while True:
response = record()
if response is None:
23
continue
else:
main(response)
except KeyboardInterrupt:
return
def main(query):
add_data(query)
intent = chat(query)
done = False
if ("google" in query and "search" in query) or ("google"
in query and "how to" in query) or "google" in query:
googleSearch(query)
return
elif ("youtube" in query and "search" in query) or "play"
in query or ("how to" in query and "youtube" in query):
youtube(query)
return
elif "distance" in query or "map" in query:
get_map(query)
return
if intent == "joke" and "joke" in query:
joke = get_joke()
if joke:
speak(joke)
done = True
elif intent == "news" and "news" in query:
news = get_news()
if news:
speak(news)
done = True
elif intent == "ip" and "ip" in query:
ip = get_ip()
if ip:
speak(ip)
done = True
elif intent == "movies" and "movies" in query:
speak("Some of the latest popular movies are as
follows :")
get_popular_movies()
done = True
elif intent == "tv_series" and "tv series" in query:
speak("Some of the latest popular tv series are as
follows :")
get_popular_tvseries()
done = True
elif intent == "weather" and "weather" in query:
city = re.search(r"(in|of|for) ([a-zA-Z]*)", query)
if city:
24
city = city[2]
weather = get_weather(city)
speak(weather)
else:
weather = get_weather()
speak(weather)
done = True
elif intent == "internet_speedtest" and "internet" in
query:
speak("Getting your internet speed, this may take some
time")
speed = get_speedtest()
if speed:
speak(speed)
done = True
elif intent == "system_stats" and "stats" in query:
stats = system_stats()
speak(stats)
done = True
elif intent == "image_generation" and "image" in query:
speak("what kind of image you want to generate?")
text = record()
speak("Generating image please wait..")
generate_image(text)
done = True
elif intent == "system_info" and ("info" in query or
"specs" in query or "information" in query):
info = systemInfo()
speak(info)
done = True
elif intent == "email" and "email" in query:
speak("Type the receiver id : ")
receiver_id = input()
speak("Tell the subject of email")
subject = record()
speak("tell the body of email")
body = record()
success = send_email(receiver_id, subject, body)
if success:
speak('Email sent successfully')
else:
speak("Error occurred while sending email")
done = True
elif intent == "select_text" and "select" in query:
sys_ops.select()
done = True
elif intent == "copy_text" and "copy" in query:
sys_ops.copy()
done = True
25
elif intent == "paste_text" and "paste" in query:
sys_ops.paste()
done = True
elif intent == "delete_text" and "delete" in query:
sys_ops.delete()
done = True
elif intent == "new_file" and "new" in query:
sys_ops.new_file()
done = True
elif intent == "switch_tab" and "switch" in query and
"tab" in query:
tab_ops.switchTab()
done = True
elif intent == "close_tab" and "close" in query and "tab"
in query:
tab_ops.closeTab()
done = True
elif intent == "new_tab" and "new" in query and "tab" in
query:
tab_ops.newTab()
done = True
elif intent == "close_window" and "close" in query:
win_ops.closeWindow()
done = True
elif intent == "switch_window" and "switch" in query:
win_ops.switchWindow()
done = True
elif intent == "minimize_window" and "minimize" in query:
win_ops.minimizeWindow()
done = True
elif intent == "maximize_window" and "maximize" in query:
win_ops.maximizeWindow()
done = True
elif intent == "screenshot" and "screenshot" in query:
win_ops.Screen_Shot()
done = True
elif intent == "stopwatch":
pass
elif intent == "wikipedia" and ("tell" in query or "about"
in query):
description = tell_me_about(query)
if description:
speak(description)
else:
googleSearch(query)
done = True
elif intent == "math":
answer = get_general_response(query)
if answer:
26
speak(answer)
done = True
elif intent == "open_website":
completed = open_specified_website(query)
if completed:
done = True
elif intent == "open_app":
completed = open_app(query)
if completed:
done = True
elif intent == "note" and "note" in query:
speak("what would you like to take down?")
note = record()
take_note(note)
done = True
elif intent == "get_data" and "history" in query:
get_data()
done = True
elif intent == "exit" and ("exit" in query or "terminate"
in query or "quit" in query):
exit(0)
if not done:
answer = get_general_response(query)
if answer:
speak(answer)
else:
speak("Sorry, not able to answer your query")
return
if __name__ == "__main__":
try:
listen_audio()
except:
print("EXITED")
Full code available on GitHub.
27
CHAPTER 7
TESTING
7.1 Test Results
7.1.1 Test Case 1
Test Case No. 1

Test Type Functional Test
Name of Test Verify weather report feature
Test Case Description The objective of this test case is to verify that the virtual voice
assistant is able to fetch and deliver the weather report for a
specified city or the current device's location.
Input Speak “what’s the weather in CITY”
OR
Speak “what’s the weather today”
Expected Output The virtual voice assistant should be able to deliver accurate
weather reports for different cities or the current device's location.
Actual Output The virtual voice assistant responds with news latest headlines.
Result Pass
Comments Working properly.
7.1.2 Test Case 2
Test Case No. 2

Name of Test Verify image generation feature
assistant is able to generate an image based on the user's prompt.
Input Speak “generate an image”
After invoking the feature a text prompt must be given
“(text prompt to generate image)”
Expected Output “What kind of image you want to generate?”
“Generating image please wait…”
28
The virtual voice assistant should display the generated image.
Actual Output The virtual voice assistant generates image as expected.
Result Pass
7.1.3 Test Case 3
Test Case No. 3

Name of Test Verify email sending feature
assistant is able to send emails to a specified recipient.
Input Speak “send email”
Provide the recipient email address, subject, and body of the
email.
Expected Output If the email is sent successfully, the virtual voice assistant should
respond with "Email sent successfully".
If there is an error while sending the email, the virtual voice
assistant should respond with "Error occurred while sending
email".
Actual Output The virtual voice assistant responds as expected.
Result Pass
7.1.4 Test Case 4
Test Case No. 4

Name of Test Verify math feature
assistant is able to solve simple mathematical equations.
Input Speak “what is the sum of 255 and 365”
Expected Output 620
29
Actual Output The virtual voice assistant calculates as expected.

Result Pass
Comments Working properly. Works accurate for simple equation.
7.1.5 Test Case 5
Test Case No. 5

Name of Test Verify opening website and app feature
assistant is able to open websites and apps in the user's system.
Input Speak “open APP_NAME”
OR
Speak “open WEBSITE_NAME”
Expected Output The virtual voice assistant should open websites and apps in a
timely manner.
Actual Output The virtual voice assistant opens apps and websites as expected.
Result Pass
Comments Working properly. Opens installed apps and websites present in
websites.py file.
7.1.6 Test Case 6
Test Case No. 6

Name of Test Verify chat history feature
assistant is able to show the previous chats with date and time.
Input Speak “show chat history”
Expected Output The virtual voice assistant should display the previous chats with
date and time in a timely manner.
Actual Output The virtual voice assistant displays chat history as expected.
30
Result Pass
7.1.7 Test Case 7
Test Case No. 7

Name of Test Verify Google search feature
assistant is able to perform Google searches as per user's
command.
Input Speak “search google for XYZ”
Expected Output The virtual voice assistant should open a new webpage and
perform a Google search for the topic specified by the user.
Actual Output The virtual voice assistant performs Google search as expected.
Result Pass
7.1.8 Test Case 8
Test Case No. 8

Name of Test Verify YouTube video play feature
assistant is able to play specified videos on YouTube as per user's
command.
Input Speak “play XYZ video”
Expected Output The virtual voice assistant should open a new webpage and play
the specified video on YouTube.
Actual Output The virtual voice assistant plays YouTube videos as expected.
Result Pass
31
7.1.9 Test Case 9
Test Case No. 9

Name of Test Verify map display feature
assistant is able to display maps of specified locations and routes
as per user's command.
Input Speak “show the map of CITY”
OR
Speak “show distance between CITY1 and CITY2”
Expected Output The virtual voice assistant should open a new webpage and
display the map of the specified location.
OR
The virtual voice assistant should open a new webpage and
display the route and distance between the two specified locations.
Actual Output The virtual voice assistant display maps and routes as expected.
Result Pass
7.1.10 Test Case 10
Test Case No. 10

Test Type Unit Test
Name of Test Verify exit functionality
assistant is able to terminate itself as per user's command.
Input Speak “exit”
Expected Output The virtual voice assistant should terminate itself with exit code 0.
Actual Output The virtual voice assistant terminate itself as expected.
Result Pass
32
CHAPTER 8
CONCLUSION AND FUTURE ENHANCEMENT
Conclusion:
In conclusion, the voice assistant developed in this project is capable of performing various
tasks such as browsing the internet, sending emails, generating images, and interacting with
the user through conversation. It is able to do so by utilizing various APIs and technologies
such as stability_sdk, Google Speech Recognition, and SMTP. The voice assistant is also
able to perform system tasks such as opening and closing tabs, windows, and applications,
as well as taking screenshots and manipulating text in the clipboard.
Future Enhancement:
There are several potential areas for future enhancement for the voice assistant. One
possibility is to improve the natural language processing capabilities of the chatbot model, in
order to enable more seamless conversation with the user. Another possibility is to expand
the range of tasks that the voice assistant can perform, for example by integrating with more
APIs and services. Additionally, the voice assistant could be made more user-friendly by
adding features such as voice prompts and visual feedback. By continuing to improve and
expand upon the functionality of the voice assistant, it has the potential to become a valuable
tool for users looking to streamline their daily tasks and improve their productivity.
33
CHAPTER 9
SCREENSHOTS
1. A Desktop View
34
35
36
CHAPTER 10
REFERENCES
[1] Kumar. Personal Assistant. Github, Jan 13, 2021.

(https://github.com/roshan9419/PersonalAssistantChatbot)
[2] Jamie Alexandre, David Marx, Stephan Auerhahn, John Sabath, Arijit Basu, Wes Brown,
Jacob Kelley, Frankwin Faber and Chris Allen. SDK for interacting with stability.ai APIs
(e.g. stable diffusion inference). Dec 01, 2022. (https://github.com/Stability-AI/stability-sdk)
[3] Anonymous. Sending Emails via Gmail with Python. Script Reference, Sep 23, 2020.
(https://scriptreference.com/sending-emails-via-gmail-with-python/)
[4] Amila Viraj. How To Build Your Own Chat Bot Using Deep Learning. Towards Data
Science, Nov 1, 2020. (https://towardsdatascience.com/how-to-build-your-own-chatbot-
using-deep-learning-bb41f970e281)
37

Project Report GitHub

Uploaded by

Copyright:

Available Formats

Project Report GitHub

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Project Report GitHub

Uploaded by

Copyright:

Available Formats

CONTENTS

Sl No Chapter Name Page No

1.1 Introduction to Voice Assistants

1.2 Aim and Purpose

2.1 Survey on Virtual Assistant: Google Assistant,

2.2 Survey on Smart Virtual Voice Assistant

2.3 Survey on Personal Assistant

2.4 Survey on Personal Desktop Virtual Voice

2.5 Smart Home Voice Assistants: A Literature Survey

3.1 Overview of existing systems

3.2 Limitations of existing system

4.1 Introduction of proposed system

4.3 System Architecture

5.1 Requirement Analysis

5.2 Data Flow Diagram

5.4 Use Case Diagram

7.2 Test Results

Sl No Figure Name Page No

2 Level 0 data flow diagram 18

3 Level 1 data flow diagram 18

4 Level 2 data flow diagram 19

6 Use Case Diagram 21

1.1 Introduction to Voice Assistants

1.2 Aim and purpose

There is an increased overall awareness and a higher level of comfort demonstrated

2.1 Survey on Virtual Assistant: Google Assistant, Siri, Cortana, Alexa

Authors: Amrita S. Tulshan and Sudhir Namdeorao Dhage

2.2 Survey On Smart Virtual Voice Assistant

2.3 Survey on Personal Voice Assistant

Authors: S. Lahari, A. Naveen, G. Sarath Chandra

2.4 Survey on Personal Desktop Virtual Voice Assistant using Python

3.1 Overview of existing system

3.2 Disadvantages of existing system

 It can perform system operations such as opening/closing/switching tabs,

4.2 Advantages of Proposed System

 It can create an image from the given text.

 Send email to specified mail id by dictating the message.

 Modification can be done quickly and easily.

 It maintains privacy as user data is not shared with third parties.

4.3 System Architecture

Figure 4.4.1 System Architecture (Voice Assistant)

5.1 Requirement Analysis

In order to effectively design and develop a system, it is important to understand and

5.2 Data Flow Diagram

 Level 0 data flow diagram

Figure 5.2.1 Level 0 Data Flow Diagram

 Level 1 data flow diagram

Figure 5.2.2 Level 1 Data Flow Diagram

 Level 2 data flow diagram

Figure 5.2.3 Level 2 Data Flow Diagram

Figure 5.3.1 ER Diagram (Voice Assistant)

Figure 5.4.1 Use Case Diagram (Voice Assistant)

# load trained model

# load tokenizer object

# load label encoder object

truncating='post', maxlen=max_len), verbose=False)

Full code available on GitHub.

7.1 Test Results

7.1.1 Test Case 1

Test Case No. 1