Virtual Assistance Using Python

ISSN (Online) 2581-9429
IJARSCT
International Journal of Advanced Research in Science, Communication and Technology (IJARSCT)
Impact Factor: 7.301 Volume 3, Issue 2, April 2023
Virtual Assistance using Python

Pranav Ambhore1, Pavan Ingole2, Ritesh Shinde3, Vedant Jadhav4, Prof. S. L. Dawkhar5
Students, Department of Information Technology1
Professor, Department of Information Technology2,3,4,5
Sinhgad College of Engineering, Pune, Maharashtra, India
Abstract: The paper explores the potential of utilizing new technology to develop an intelligent Virtual
Assistant that is capable of using natural language processing and user-based data. It examines existing
intelligent programs with different categories of support and evaluates the potential usefulness of a
particular software as a Virtual Assistant. The proposed Virtual Assistant should be able to communicate
socially through natural language processing, store and analyze user data, and operate without the need
for human input or programming. The paper suggests that with advancements in technology, creating
virtual personal assistants could become a reality. The authors conducted experiments on a specific
software and performed user testing, which demonstrated that a basic program with natural language
processing algorithms could already be viable. Overall, the paper presents the idea of an intelligent Virtual
Assistant that could revolutionize the way we interact with technology.
Keywords: Python programming language, Natural Language Processing (NLP), Wolfram Alpha API,
desktop assistants, machine learning, text-to-speech, speech-to-text, language processing, voice recognition,
artificial intelligence, Internet of Things (IoT), and virtual assistants.
I. INTRODUCTION
The primary objective of this project is to create a straightforward and self-contained application that can assist
individuals with limited technical expertise or computer literacy in using their computers. As computers have become
increasingly affordable and indispensable in daily life, this application aims to provide a solution for those who may
feel overwhelmed by technology.
The application functions in a manner similar to popular virtual assistants such as Siri and Google Assistant, with a
focus on providing assistance for personal computers. Users can access the virtual assistant through voice commands,
keyboard inputs, or remotely via the internet.
The system comes with a set of predefined commands, and users have the option of adding their own custom
commands. The virtual assistant can notify users of incoming emails, provide information about the weather and their
location, and even reveal IP addresses, MAC addresses, and wireless network passwords. Additionally, users can use
voice commands to perform system tasks like shutting down or putting their computer to sleep.
The application also includes a note-taking feature. The system boasts an interface that can take inputs and produce
outputs. For various tasks, such as time management and search, there are separate modules. The interface utilizes these
modules to execute commands and perform tasks in an efficient and user-friendly manner. The ultimate goal is to make
computer usage simpler for individuals with limited technical expertise and promote ease of use.
This project centers around the development of a Windows-based personal assistant utilizing voice recognition
technology. The application provides a range of services and functions, including mail sending, event handling, location
services, music player support, weather checks, Google and Wikipedia search engines, camera integration, and
Bluetooth headset compatibility. By integrating several commonly used desktop services, this program has the potential
to significantly enhance daily life and make it more convenient. Moreover, it can be especially helpful for individuals
with physical disabilities who may face challenges with manual operations. This program was inspired by Apple's
popular virtual assistant, "Siri," which is part of the reason why it was chosen as the subject for a diploma project.
This application was initially launched in conjunction with the release of the iPhone4S. It's a highly engaging and user-
friendly tool with broad applicability and considerable potential for further development. It's not limited to any
particular generation or profession, and can be deployed across a wide range of industries. However, as it's currently
Copyright to IJARSCT DOI: 10.48175/IJARSCT-9131 284

www.ijarsct.co.in
IJARSCT
only available for Apple's iOS, we've introduced a "Virtual Assistant" for personal computers to address this limitation.
Voice assistance is particularly valuable for personal assistants, navigation, driving, and supporting individuals with
disabilities, among other use cases.
Wikipedia describes "Siri" as an intelligent personal assistant and knowledge navigator designed for use with Apple's
iOS. The application leverages a natural language user interface to answer questions, offer recommendations, and
perform actions by delegating requests to a set of web services. According to Apple, the software adapts to individual
user preferences over time, personalizing results and completing tasks such as identifying nearby restaurants and
providing directions.
II. LITERATURE SURVEY

Speech recognition technology has evolved through several waves of major innovations and has now become a standard
feature on smartphones and wearable devices, enabling dictation, search, and voice commands. The goal of designing a
compact, efficient, and accurate large vocabulary speech recognition system for computers has been a major focus of
research. A set of techniques have been developed to improve the performance of automated voice search services,
especially for Windows users accessing these services through portable devices.
Machine learning and natural language processing techniques have been refined, and applications that provide speech-
based services and content have emerged. As computers become smaller and more ubiquitous, such as with wearables
and Internet of Things (IoT) devices, speech recognition technology is becoming more important. The primary function
of a speech recognizer is to convert spoken words into text or other forms of data.
One example of a widely used speech recognition application is "SIRI" on iPhones. SIRI serves as a personal assistant
with voice recognition intelligence, enabling users to communicate with their mobile devices using voice commands.
SIRI processes the user's input and provides responses in various forms, such as performing an action or providing
information. This proposed system can change the way users interact with their devices and make it more convenient
for Windows users.
Cortana, a desktop-based virtual assistant, offers a range of features including reading messages, tracking location,
monitoring browsing history, checking contact lists, and integrating this data to suggest helpful information if allowed.
Alternatively, users can type their queries or requests if they prefer not to speak out loud.
Siri, which has been part of iOS since its launch in 2011 with iOS 5, initially provided basic features such as weather
and messaging. However, it has expanded significantly to support more third-party integrations with MacOS. While Siri
is known for its humor, the virtual assistant is becoming more capable with time. It can now make calls, send messages,
schedule meetings, launch apps and games, play music, answer questions, set reminders, and provide weather forecasts.
Google Assistant is different from Cortana and Siri. It has incorporated the features of the older Google Now, which is
being phased out.
A. Background of the Industry Based

The basis of this project stems from Apple's popular application, "Siri," which was launched alongside the iPhone4S.
This user-friendly application has a wide range of real-world applications and great potential for development, making
it suitable for many different industries. However, the application is not available for Windows, prompting the
development of a "Virtual Assistant" for personal computers. The voice-assisted technology has proven useful for
personal assistants, navigational tools, driving aids, and the disabled community, among others. Siri is an intelligent
personal assistant that serves as an iOS application for Apple devices. It uses a natural language interface to answer
questions, provide recommendations, and perform tasks by accessing web services.Apple claims that the software learns
and adapts to the user's preferences over time, resulting in personalized results such as restaurant recommendations and
directions.
B. Information Retrieval
The program encompasses a range of functions and services, including mail exchange, mathematical calculations,
location services, music player service, weather checking, Google and Wikipedia search engines, camera, Bluetooth

www.ijarsct.co.in
IJARSCT
headset support, IP address finding, Saved Wi-Fi passwords finding, and a help menu. Each function has specific
information and requirements, as outlined below.
Mail exchange allows customers to send emails to individuals in their contacts. A correct command containing the mail
request keyword and destination person should result in the recipient receiving the email.
Location services enable users to check their current location or find a desired destination. Depending on the request
category, the user should receive an easily understandable map with the relevant locations.
The music player service offers users the ability to play a specific or randomly selected song from the prestored song
list on their desktop PC. The music can be stopped at any time.
The weather checking function allows users to check the weather in any location, with information such as temperature
and humidity included. Additionally, users can check the weather for the current day, tomorrow, or the next four days.
The program includes a Google search engine that allows users to search for anything on Google, with the results
displayed on their web browser. There is also a Wikipedia search engine that enables users to search for anything on
Wikipedia, with the searched content displayed on the browser.
The camera function calls the mobile phone camera to take a picture of the current view, which is then stored in the
gallery for later viewing and operation.
To overcome the issue of voice recognition being difficult when the music player is playing or the surroundings are
noisy, the program offers Bluetooth headset support, allowing users to speak to the headset rather than the PC if
enabled.
The program also features an application opening and closing service, enabling users to open any installed applications
such as MS Word, MS PowerPoint, Paint, Notepad, IDEs, Text Editors, File Explorer, and more.
For programmers and IT personnel, the program includes an IP address service that allows users to find the hostname
and IP address of their PC, as well as a MAC address finding service.
A wireless network password finding service is also available to find saved WiFi passwords, while a note writing
service uses the speech-to-text module for easy Dictation.
The program also includes a joke service for entertainment purposes, a time and date service for telling the current time,
date, or day, and a calculation service for mathematical operations such as multiplication, division, sin, cos values, and
more.
C. Theory Model
This project encompasses various aspects of software engineering principles, software development models, Python
programming skills, APIs, and network communication technologies. The use of APIs and web services in this project
is focused on the Wolfram Alpha API, eliminating the need for developers to write additional code as the API handles
the execution. Therefore, API serves as an important concept and guides the development theory
The Wolfram Alpha Web service API provides a web-based API that facilitates the integration of Wolfram Alpha's
computational and presentation capabilities into web, mobile, desktop, and enterprise applications. Wolfram Alpha is an
API that utilizes Wolfram's algorithms, knowledgebase, and AI technology to compute expert-level answers. This
functionality is made possible by the Wolfram Language. This article provides instructions on how to create a simple
assistant application in Python that can answer basic questions.
Figure 1
www.ijarsct.co.in
IJARSCT
The user's input will be sent to Wolfram Alpha for processing. If a response is received, it will be returned to the user. If
no response is received, the input will be interpreted as a keyword(s) and used for a Wikipedia search query.
III. EQUIPMENT – CHOICE OF MATERIALS

A. Tools and Environment Development:
 Python 3: Python is a high-level, object-oriented, interactive, and general-purpose programming language.
Python 3.0 was introduced in 2008, which is incompatible with the earlier version, but several critical features
have been backported to make it compatible with version 2.7.
 Visual Studio Code: Microsoft created a source-code editor that works on Windows, Linux, and macOS. It
has debugging support, integrated Git control and GitHub, syntax highlighting, intelligent code completion,
code snippets, and refactoring capabilities.
 Sublime Text: It is a shareware cross-platform source code editor that includes a Python API. It is compatible
with many programming and markup languages, and plugins can be added by users, typically community-built
and maintained under free-software licenses.
B. API and Python Libraries

 Google Speech API: Speech recognition is an essential function in numerous applications such as home
automation, artificial intelligence, etc. This article introduces the use of Python's SpeechRecognition library. It
is useful as it can be used on microcontrollers such as Raspberry Pi with an external microphone. We chose
Google Speech API since it has an excellent Speech Recognition API. This API translates spoken text
(microphone) into written text (Python strings), briefly known as Speech to Text. By speaking into a
microphone, Google API converts it into written text. The API provides excellent results for the English
language.
 Wolfram Alpha API: The API enables clients to submit free-form queries similar to those entered on the
Wolfram|Alpha website, and the computed results are returned in various formats. It uses a standard REST
protocol.
The pyttsx3 library in Python is a text-to-speech conversion tool. It operates offline and is compatible with both Python
2 and 3, making it a suitable choice over other libraries.
IV. CONCLUSION
The Project Development and Implementation
The program focuses mainly on developing Windows-based software using Python programming language, various
APIs for Google products, and API for mathematical operations, among others. The project was developed by a team of
three developers and follows the Incremental model and Extreme programming model. During the six-month
development process, the team followed the same cycle in each phase of analyzing requirements, designing,
implementing solutions in pair programming mode, and testing the results. The development process was guided by a
primary planning strategy that defined how to work with the program, how much time to spend each week, the
necessary resources for development, and how to handle problems that arose.
The project was efficiently completed under this development model, and the resources found early on were useful
during implementation.
Project Usage & Potential Prospects

The project is highly useful and has significant potential for use in various industries. Although the program's primary
focus is on creating a virtual assistant on Windows-based systems using voice, the concept of speech recognition can be
applied in different industries. Speech recognition technology can be more convenient, save time, and be helpful,
especially for people with manual operation difficulties. The program is a collection of 15-20 functions that are
frequently used on a Windows PC, and users can enjoy different services within this platform. It is easy to use with
simple operations compared to traditional working strategies where users must know how to work with desktop

www.ijarsct.co.in
IJARSCT
systems. Additionally, the program's voice-operated feature is helpful for people who prefer voice operation and those
who have difficulties/disabilities with manual operations. The primary objective of the program is to provide services
using voice and make it accessible to more people.
REFERENCES
[1]. S Subhash; Prajwal N Srivatsa; S Siddesh; A Ullas; B Santhos. Artificial Intelligence-based Voice Assistant,
IEEE, 2020. https://ieeexplore.ieee.org/document/9210344/
[2]. EV Polyakov, MS Mazhanov, AY Voskov, LS Kachalova, MV and SV Polyakov, "Investigation and
development of the intelligent voice assistant for the IOT using machine learning", Moscow workshop on
electronic technologies, 2018.
[3]. Veton Kepuska and Gamal Bohota, "Next generation of virtual assistant (Microsoft Cortana Apple Siri
Amazon Alexa and Google Home)", IEEE conference, 2018.
[4]. Laura BURbach, Patrick Halbach, Nils Plettenberg, Johannes Nakyama, Matrina Ziefle and Andre Calero
Valdez, "Ok google Hey Siri Alexa. Acceptance relevant of virtual voice assistants", International
communication conference IEEE, 2019
[5]. X. Lei, G. Tu, A. X. Liu, C. Li and T. Xie, "The insecurity of home digital voice assistants - amazon alexa as
a case study", CoRR, vol. abs/1712.03327, 2017.
[6]. J. Gratch, N. Wang, J. Gerten, E. Fast and R. Duffy, "Creating rapport with virtual agents" in Intelligent
Virtual Agents, Berlin, Heidelberg:Springer Berlin Heidelberg, pp. 125-138, 2017.
[7]. B. Weiss, I. Wechsung, C. Kühnel and S. Möller, "Evaluating embodied conversational agents in multimodal
interfaces", Computational Cognitive Science, vol. 1, pp. 6, Aug 2015.
[8]. Y. Matsuyama, A. Bhardwaj, R. Zhao, O. Romeo, S. Akoju and J. Cassell, "Socially-aware animated
intelligent personal assistant agent", Proceedings of the 17th Annual Meeting of the Special Interest Group
on Discourse and Dialogue, pp. 224-227, 2016.
[9]. M. Schroeder, E. Bevacqua, R. Cowie, F. Eyben, H. Gunes, D. Heylen, et al., "Building autonomous
sensitive artificial listeners", IEEE transactions on affective computing, vol. 3, pp. 165-183, 2018.
[10]. Hannun, C. Case, J. Casper, B. Catanzaro, G. Diamos, E. Elsen, et al., "Deep speech: Scaling up end-to-end
speech recognition", CoRR, vol. abs/1412.5567, 2014.
[11]. M. Schröder and J. Trouvain, "The german text-to-speech synthesis system mary: A tool for research
development and teaching", International Journal of Speech Technology, vol.
[12]. P. Cosi, F. Tesser, R. Gretter, C. Avesani and M. Macon, "Festival speaks italian!" in EUROSPEECH 2001
Scandinavia 7th European Conference on Speech Communication and Technology 2nd INTERSPEECH
Event, pp. 509-512, 2001.
[13]. D. Huggins-Daines, M. Kumar, A. Chan, A. W. Black, M. Ravishankar and A. I. Rudnicky, "Pocketsphinx:
A free real-time continuous speech recognition system for hand-held devices" on Acoustics Speech and
Signal Processing Proceedings, May 2018
[14]. Think Python Book, Allen Downey
[15]. A Python Book Author: Dave Kuhlman
[16]. Python by Narayana Book

www.ijarsct.co.in

Virtual Assistance Using Python

Uploaded by

Virtual Assistance Using Python

Uploaded by

ISSN (Online) 2581-9429

Impact Factor: 7.301 Volume 3, Issue 2, April 2023