PROJECT SYNOPSIS

On

ARTIFICIAL INTELLIGENCE : DESKTOP VOICE ASSISTANT

BACHELOR OF TECHNOGOGY

Branch: Computer Science & Engineering

SUBMITTED BY GUIDE NAME

Aru Sharma (1747910008) Mrs Anu Saxena
Rajat Saxena (1747910047) (assistant professor cse deptt)
Prateek Saxena (1747910043)

Dept. of Computer Science & Engineering

Rajshree Institute of Management & Technology
National Highway 30, Pilibhit Road, Bareilly (Up)
 INTODUCTION

Artificial intelligence (AI) is intelligence demonstrated by machines, unlike the natural

intelligence displayed by humans and animals, which involves consciousness and emotionality.
The distinction between the former and the latter categories is often revealed by the acronym
chosen. 'Strong' AI is usually labelled as AGI (Artificial General Intelligence) while attempts to
emulate 'natural' intelligence have been called ABI (Artificial Biological Intelligence). Leading
AI textbooks define the field as the study of "intelligent agents": any device that perceives its
environment and takes actions that maximize its chance of successfully achieving its goals.
[3]
 Colloquially, the term "artificial intelligence" is often used to describe machines (or
computers) that mimic "cognitive" functions that humans associate with the human mind, such as
"learning" and "problem solving".[4]
As machines become increasingly capable, tasks considered to require "intelligence" are often
removed from the definition of AI, a phenomenon known as the AI effect.[5] A quip in Tesler's
Theorem says "AI is whatever hasn't been done yet."[6] For instance, optical character
recognition is frequently excluded from things considered to be AI,[7] having become a routine
technology.[8] Modern machine capabilities generally classified as AI include
successfully understanding human speech,[9] competing at the highest level in strategic
game systems (such as chess and Go),[10] and also imperfect-information games like poker,
[11]
 self-driving cars, intelligent routing in content delivery networks, and military simulations.[12]
Artificial intelligence was founded as an academic discipline in 1955, and in the years since has
experienced several waves of optimism,[13][14] followed by disappointment and the loss of funding
(known as an "AI winter"),[15][16] followed by new approaches, success and renewed funding.[14]
[17]
 After Alpha Go successfully defeated a professional Go player in 2015; artificial intelligence
once again attracted widespread global attention.[18] For most of its history, AI research has been
divided into sub-fields that often fail to communicate with each other.[19] These sub-fields are
based on technical considerations, such as particular goals (e.g. "robotics" or "machine
learning"),[20] the use of particular tools ("logic" or artificial neural networks), or deep
philosophical differences.[23][24][25] Sub-fields have also been based on social factors (particular
institutions or the work of particular researchers).[19]
The traditional problems (or goals) of AI research include reasoning, knowledge
representation, planning, learning, natural language processing, perception and the ability to
move and manipulate objects.[20] General intelligence is among the field's long-term goals.
[26]
 Approaches include statistical methods, computational intelligence, and traditional symbolic
AI. Many tools are used in AI, including versions of search and mathematical optimization,
artificial neural networks, and methods based on statistics, probability and economics. The AI
field draws upon computer science, information
engineering, mathematics, psychology, linguistics, philosophy, and many other fields.
The field was founded on the assumption that human intelligence "can be so precisely described
that a machine can be made to simulate it".[27] This raises philosophical arguments about the
mind and the ethics of creating artificial beings endowed with human-like intelligence. These
issues have been explored by myth, fiction and philosophy since antiquity.[32] Some people also
consider AI to be a danger to humanity if it progresses unabated.[33][34] Others believe that AI,
unlike previous technological revolutions, will create a risk of mass unemployment.[35]
In the twenty-first century, AI techniques have experienced a resurgence following concurrent
advances in computer power, large amounts of data, and theoretical understanding; and AI
techniques have become an essential part of the technology industry, helping to solve many
challenging problems in computer science, software engineering and operations research

TECHNOLOGY USED IN THIS PROJECT

*Python
*pyttsx3
Python | Text to Speech by using pyttsx3

FIG-: 1.1 text to speech | python

How cool is it to build your own personal assistants like Alexa or Siri? It’s not very complicated
and can be easily achieved in Python. Personal digital assistants are capturing a lot of attention
lately. Chatbots are common in most commercial websites. With growing advancements in
artificial intelligence, training the machines to tackle day-to-day tasks is the norm.

Voice based personal assistants have gained a lot of popularity in this era of smart homes and
smart devices. These personal assistants can be easily configured to perform many of your
regular tasks by simply giving voice commands. Google has popularized voice-based search that
is a boon for many like senior citizens who are not comfortable using the keypad/keyboard.
This article will walk you through the steps to quickly develop a voice based desktop assistant,
Minchu (meaning Flash) that you can deploy on any device. The prerequisite for developing this
application is knowledge of Python.

For building any voice based assistant you need two main functions. One for listening to your
commands and another to respond to your commands. Along with these two core functions, you
need the customized instructions that you will feed your assistant.

The first step is to install and import all the necessary libraries. Use pip install to install the
libraries before importing them. Following are some of the key libraries used in this program:

 The SpeechRecognition library allows Python to access audio from your system’s

microphone, transcribe the audio, and save it.

 Google’s text-to-speech package, gTTS converts your audio questions to text. The

response from the look-up function that you write for fetching answer to the question is
converted to an audio phrase by gTTS. This package interfaces with Google Translate’s
API.

 Playsound package is used to give voice to the answer. Playsound allows Python to play
MP3 files.

 Web browser package provides a high-level interface that allows displaying Web-based

pages to users. Selenium is another option for displaying web pages. However, for using
this you need to install and provide the browser-specific web driver.
 Wikipedia is used to fetch a variety of information from the Wikipedia website.

 Wolfram|Alpha is a computational knowledge engine or answer engine that can

compute mathematical questions using Wolfram’s knowledge base and AI technology.
You need to fetch the API to use this package.
 FEASIBILITY STUDY

This feasibility study examined the possibility of using an independent voice recognition system

Fg-1.3Block digram

as the input device during a training delivery requirement. The intent was to determine whether
the voice recognition system could be incorporated into a training delivery system designed to
train students how to use the Communications Electronics Operating Instructions manual, a tool
used for communicating over the radio network during military operations. This study showed
how the voice recognition system worked in an integrated voice based delivery system for the
purpose of delivering instruction. An added importance of the study was that the voice system
was an independent speech recognition system. At the time this study was conducted, there did
not exist a reasonably priced speech recognition system that interfaced with both graphics and
authoring software which allowed any student to speak to the system without training the system
to recognize the individual student's voice. This feature increased the usefulness and flexibility of
the system. The methodology for this feasibility study was a development and evaluation model.
This required a market analysis, development of the voice system and instructional course ware,
testing the system using a sample population from the Armor School at Ft. Knox, Kentucky, and
making required alterations. The data collection approach was multifaceted. There were surveys
to be completed by each subject: a student profile survey, a pretest, a posttest, and an opinion
survey about how well the instruction met expectations. Data was also collected concerning how
often the recognition system recognized, did not recognize, or misrecognized the voice of each
subject. The information gathered was analyzed to determine how well the voice recognition
system performs in a training delivery application. The findings of this feasibility study indicated
that an effective voice based training delivery system could be developed by integrating an IBM
clone personal computer with a graphics board and supporting software, signal processing board
and supporting software for audio output and input, and instructional authoring software.
Training was delivered successfully since all students completed the course, 85% performed
better on the posttest than on the pretest, and the mean gain scores more than satisfied the
expected criterion for the training course. The misrecognition factor was 12%. An important
finding of this study is that the misrecognition factor did not affect the students' opinion of how
well the voice system operated or the students' learning gain.
 METHODOLOGY/PLANNING OF WORK

The part where I tell you what are the basic requirement for this project. You’ll need Python 3.6.
We’ll be using the pyttsx3 package which is a text-to-speech library for Python. The basic reason
why we use this is because it works offline. Another basic requirement of this project will be
Python’s Speech Recognition library. There are other requirements for the project which are
listed below; we’ll understand them as we go ahead. Inappropriate college description is also
conveyed as all terms and conditions of college are not known to students. The overall system
design consists of following phases:

(a) Data collection in the form of user’s voice

(b) Voice analysis and conversion to text
(c) Data storage and processing
(d) Generating the task to be done from the processed text output
 FACILITIES REQUIRED FOR PROPOSED WORK

Desktop assistant name is NOVA and we have developed it under 5000 it will have interface in
which there will be two button start and exit. As soon as we start the application are application
will tell us to wait till it is open and we have to click start to run the application after running the
application are assistant NOVA will ask that “how can I help you?”. Then the user has to give
the voice command to the assistant. If the user gives voice command “Describe yourself”, the
NOVA results with

It provides information regarding the weather, News, it can play music, it can search for topics
on Wikipedia, can setup an alarm, Display the current date

and time.
User can collect information through this application.
It reduces both man power and time. Due to support of NLP user can ask queries in very formal
way. No need ask queries in very strict and specific way. The user should aware of general rules
of English Language. The goal is to provide people a quick and easy way to have their questions
answered.
 Source Code : Python|| voice desktop assistant

import pyttsx3
import speech_recognition as sr 
import datetime
import wikipedia
import webbrowser
import time

#set engine----------------------------------------------------------------------
----------------------------------
engine = pyttsx3.init('sapi5')
voices = engine.getProperty('voices')
rate = engine.getProperty('rate')
engine.setProperty('rate', rate - 20)
#print(voices[0].id)
engine.setProperty('voice', voices[0].id)

#-------functions1(computer speak)-----------------------------------------------
--------------------------------------------------------------

def speak(audio):
    engine.say(audio)
    engine.runAndWait()
#-----------------------(computer wish me)---------------------------------------
----------------------------------------------------
def wishMe():
    hour = int(datetime.datetime.now().hour)
    if hour>=0 and hour<=12:
        speak('Good moring aru sir!')

    elif hour>=12 and hour<=18:
         speak('good after noon aru sir!')
         
    else:
        speak ('good evening  sir!')

    speak('i am phoenix ! what can i do for you')
    #-----------------------(computer take ur voice)-----------------------------
-------------------------------------------------------

def takeCommand():
# its take micro phone input from the user and returen the string out put-------
--------------------------------------

    r = sr.Recognizer()
    with sr .Microphone() as source:
        print('Listening..')
        r.pause_threshold = 1
        audio = r.listen(source)

    try:
        print('recognizing...!!')
        query= r.recognize_google(audio, language='en-in')
        print(F"User said:  {query}\n")

    except Exception as e:
        print("say again please...")
        return "None"
    return query
    
if __name__ == "__main__":
   wishMe()#first it will wish u then take ur voice-----------------------------
---------------------------------------
   while True:
    query = takeCommand().lower()

#logic tasks--
# wikipedia work-----------------------------------------------------------------
-----------------------------------------
    if 'wikipedia' in query:
            speak('Searching Wikipedia...')
            query = query.replace("wikipedia", "")
            results = wikipedia.summary(query, sentences=2)
            speak("According to Wikipedia")
            print(results)
            speak(results)
    elif "who made you" in query: 
        speak ("I have been created by, programmer  ARU.")
        query = query.replace("who made you","")
        

    elif 'open youtube' in query:
        webbrowser.open("youtube.com")      

    elif 'the time' in query:
            strTime = datetime.datetime.now().strftime("%H:%M:%S")    
            speak(f"Sir, the time is, {strTime}")

    elif 'which college i study from' in query:
           speak(f"sir, U are study in Rajshree Institute of managment of techno
logy") 
           query = query.replace("which college i study from","")      
           
    elif  'rajat' in query:
           speak(f"sir,  He is your fast friend , and also naughty ")
           query= query.replace('rajat',"")

    elif  "thank you" in query:
           speak("your wellcome sir ")
           query= query.replace("thank you","")
 CONCLUSION

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 Jarvis with mobile using React Native to
provide a synchronised experience between the two connected devices. Further, in the long run,
Jarvis 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 Jarvis. 3
 BIBLIOGRAPHY

We owe a debt of sincere gratitude, and respect to our guide and mentor Ronak Jain, Professor, AITR,
Indore for his sagacious guidance, vigilant supervision and valuable critical appreciation throughout this
project work. We express profound gratitude and heartfelt thanks to Dr. Kamal Kumar Sethi, HOD IT,
AITR Indore for his support, suggestion and inspiration for carrying out this project. We thank you for the
support and guidance received from Dr. S C Sharma, Director, AITR, Indore whenever needed. VI.
REFERENCES [1] “Desktop Assistant from Wikipedia,” https://en.wikipedia.org/wiki/Desktop Assistant,
[2] Richard Krisztian Csaky, “Desktop Assistant and related Research paper Notes with Images,”
https://github.com/ricsinaruto/Seq2seqDesktop Assistants/wiki/Desktop Assistant-and-RelatedResearch-
Paper-Notes-eith-images, [3] Yosua Alvin AdiSoetrisno, “Ticketing Desktop Assistant Service using
Serverless NLP Technology,” http://www.academia.edu/Documents/in/Desktop Assistant, [4] “Potential
benefits of Desktop Assistants,”
https://www.convinceandconvert.com/wpcontent/uploads/2018/01/Critical-Desktop Assistant-Statistics-
2018-2-e1516922252367.jpg, [5] “Desktop Assistant Theory Explained,”
https://www.geeksforgeeks.org/Desktop Assistant-theoryexplained/, [6] [6] “Freya Riki, “Future of
Desktop Assistant in 2019,” https://yourstory.com/mystory/future-of-Desktop Assistant-in-2019-
8wulieg1yx,