Scribd
Upload
22 views

3-2 Project Report

Uploaded by

nazmul.kuet31
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
22 views

3-2 Project Report

Uploaded by

nazmul.kuet31
Copyright
© © All Rights Reserved
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 6

Khulna University of Engineering and Technology, Khulna-9203

Department of Electronics and Communication Engineering


Course No: ECE-3200
Course Title: Electronics Project Design/ Development
3rd Year, 2nd Term
Report on AI Virtual Assistant

Supervised By: Submitted By:


Md. Foysal Md. Rabiul Hasan
Assistant Professor Roll: 1709017
Dept. of ECE Md. Tawfik Alahi Tanvir
KUET, Khulna-9203 Roll: 1709014
Nazmul Hasan
Roll: 1709031
Dept. of ECE
KUET, Khulna-9203

Date of Submission: 24.03.2022


Contents:
1. Objectives
2. Introduction
3. Theory
4. Type of AI
5. Methodology
a. Features
b. Programming Libraries
c. Working Procedure
6. Application
7. Conclusion

Objectives:
1. Helps with time and Make life more comfortable and specialized for handicap people.
2. Daily management through voice recognition.
3. Make schedule management.

Introduction:
AI Virtual Assistant or AI Assistant or Digital Assistant is a voice command comprehension
program by users. Companies are trying to replace the computer with any human task by
automation. The objective of AI virtual assistants is to replace secretaries and personal assistants.
Those who performs tasks such as reading text and dictation, finding phone numbers and making
calls, emailing schedules and meeting reminders, etc.
Artificial Intelligence is an approach to make a computer, a robot, or a product to think how
smart human think. AI is a study of how human brain think, learn, decide and work, when it tries
to solve problems and finally this study outputs intelligent software systems.

Theory:
Artificial Intelligence enables computers and machines to mimic the perception, learning,
problem-solving, and decision-making capabilities of the human mind. AI assistants are typically
a cloud-based program that requires an internet connection to work like Siri, Google Assistant,
and Cortana. AI voice assistants power massive amounts of data. This data is similar to data
feeds on AI platforms such as machine learning, platforms for speech recognition, and NLP.
Types of Artificial Intelligence:
1. Weak AI:
 Also called narrow AI or (ANI)
 AI is trained and focused for specific tasks
 Examples: Apples' Siri, Amazon’s Alexa, IBM Watson

2. Strong AI:
 Also called Artificial General Intelligence
 AI that more fully replicates the autonomy of the human brain
 It is still in theoretical phase.

Methodology:
Feature:
 Weather Forecasting
Numerical Weather Prediction, for example, is one such tool that can assist AI in weather
forecasting. Ensemble Neural Network, Radial Basis Function Network, Back
Propagation Network, Genetic Algorithm, and Fuzzy Clustering are some other AI
techniques for weather prediction
 Tell us News
Whenever it is called, it instantly tells us news update.
 Open Websites
It can open any website just like facebook, youtube etc.
 Tell us Jokes
It tells randomly any jokes from the internet.
 Tell us Time and Date
When we need to know about the time and date, it utters just telling it.
 Tell us almost anything we ask
We can ask anything, it returns answer using the Google.

Programming Libraries:
 Speech Recognition:
Library for performing speech recognition, with support several engines and APIs, online
and offline.
 PyAudio:
PyAudio is required if and only if we want to use microphone as input.
 Random:
To take random variable.
 JarvisAI:
Jarvis AI is a Python module which is able to perform task like Chatbot,Assistant etc. It
provides base functionality for any assistant application.This JarvisAI is build using
Pytorch.TensorFlow, Transformers and open-libraries.
 Numpy:
NumPy is a Python library used for working with arrays
 Pipwin:
Pipwin installs compiled python binaries on windows
 PlaySound:
The playsound module is a cross platform module that can play audio files. This doesn't
have any dependencies, simply install with pip in your virtualenv and run
 GTTS (Google Text to Speech):
a Python library and CLI tool to interface with Google Translate's text-to-speech API.

Working Procedure:

Wake word Natural Language Processing

Automatic Speech Recognition

Python Background

Voice
Text to Speech Dialogue Management
Object creation:
Obj = JarvisAI.JarvisAssistant()
We have created this ‘t2s(text)’ function. This will convert any text to speech. The entire
program we will use (call) this function to produce speech from text.
def t2s(text):
obj.text2speech(text)
We want to continuously listen to input from the user, so this ‘mic_input ()’ will try to fetch
audio from the computer’s microphone continuously. It will process the audio and return text in
‘res’ variable. We can use this ‘res’ variable to perform some action according to user input.
while True:
res=obj.mic_input ()

Application:
 Healthcare sectors: To analyze links between prevention or treatment approaches and
patient outcomes.
 Business Management: Hiring and Recruitment, Cybersecurity, Market prediction,
Customer Analysis, Billing and Invoice etc.
 Home Automation: To interact with each other and acquire new data that assists in
learning human habits.
 Automobiles Industry: Design, supply chain, production, and post-production.
 Video Processing: Trained models, able to detect certain objects
 Image Processing: Detecting and recognizing objects and patterns in images and videos

Challenges:
 Computing Power. The amount of power these power-hungry algorithms use is a factor
keeping most developers away.
 Trust Deficit.
 Limited Knowledge.
 Human-level.
 Data Privacy and Security.
 The Bias Problem.
 Data Scarcity.
Conclusion:
AI virtual assistants for 2022 are rapidly evolving. Different companies allow them to provide
more capabilities, such as advancements in speech recognition and natural language processing.
As a beginners we have worked with some features of it and successfully executed the program.
To better prepare for the future society in which artificial intelligences (AI) will have much more
pervasive influence on our lives, a better understanding of the difference between AI and human
intelligence is necessary. Human and biological intelligence cannot be separated from the
process of self-replication.

You might also like