IJARCCE ISSN (O) 2278-1021, ISSN (P) 2319-5940

International Journal of Advanced Research in Computer and Communication Engineering

ISO 3297:2007 CertifiedImpact Factor 7.918Vol. 12, Issue 3, March 2023
DOI: 10.17148/IJARCCE.2023.12324

Personal Desktop Voice Assistant - Research

Paper
1Sakshi R Jain, 2Prof Feon Jason
1
Master Student, School of CS & IT, Jain University, Bengaluru, India
2
Professor, School of CS & IT, Jain University, Bengaluru, India

Abstract: The term "virtual assistant" refers to a software agent that can carry out tasks or provide services on behalf of
a person. Virtual assistants that may be accessed through online chat are occasionally referred to as "chatbots" in general
or in relation to just those. The term "virtual assistant" (VA) refers to computer-simulated settings that can mimic physical
presence in both the actual world and made-up universes. In order to construct an intelligent Virtual Personal Assistant
(VPA), new technology could be used in a number of ways, with a focus on user-based data. The goal of this project is
to provide technical information about virtual assistant technology, including its advantages and disadvantages in many
contexts. The project focuses on virtual assistant types and structural elements of a virtual assistant system. This research
paper explores the development and application of Personal Desktop Voice Assistants in various domains. The study
focuses on the use of natural language processing and machine learning algorithms to enable voice-activated commands,
and their ability to learn and adapt to individual user preferences. The paper reviews the current state-of-the-art in Personal
Desktop Voice Assistants, including their capabilities, limitations, and potential applications. It examines the impact of
these technologies on productivity, efficiency, and accessibility for individuals with disabilities. The research also
considers the ethical and privacy implications of Personal Desktop Voice Assistants, including data collection, storage,
and usage. It explores the need for transparency, consent, and accountability in the development and deployment of these
technologies. The paper presents a case study on the integration of Personal Desktop Voice Assistants in healthcare,
highlighting their potential to improve patient outcomes, reduce healthcare costs, and enhance patient satisfaction.
Overall, this research paper provides a comprehensive overview of Personal Desktop Voice Assistants, their current state-
of-the-art, and future directions. It highlights the potential benefits and challenges associated with the integration of this
technology into various domains, and the need for responsible and ethical development and deployment.

I.INTRODUCTION

With time, computers have become increasingly significant tools that are also getting cheaper. The goal of the personal
virtual assistant is to provide a trustworthy, affordable, and simple to use helper. The term "virtual assistant" (VA) refers
to computer-simulated environments that can approximate physical presence in both real-world and fictional settings. A
real-time and interactive technology is a virtual assistant. It implies that the computer can instantly alter the virtual reality
in response to user input. The user's perception of being a part of the action in their environment is enhanced through
interaction and its gripping power. A high-level encounter can be had by utilising all human sensory pathways. The
majority of virtual assistant environments today are primarily visual, shown on a computer screen, but some simulations
also contain extra sensory data, such sound through speakers or headphones. The development of virtual assistants has
shown promise in a number of fields, including training simulators, medicine and health care, rehabilitation, education,
engineering, scientific visualisation, and the entertainment sector. The software functions similarly to Siri and Google
Assistant. Yet, the primary focus of the application is the computer. A voice assistant is a digital assistant that helps
people through gadgets and voice recognition software by using speech synthesis, natural language processing, and voice
recognition. The foundation of this research is speech recognition, one of the fundamental ideas in artificial intelligence.

II.APPLICATION OF PERSONAL DESKTOP VOICE ASSISTANT

Voice assistants can do the following basic functions:

o Web search
o Play music or videos
o Set reminders and alarms
o Launch any programme or application
o Receive weather updates
o Send emails, WhatsApp, etc.
These are only a few instances of the jobs that voice assistants can complete; we can conduct a great deal more depending

© IJARCCE This work is licensed under a Creative Commons Attribution 4.0 International License 126
 IJARCCE ISSN (O) 2278-1021, ISSN (P) 2319-5940

International Journal of Advanced Research in Computer and Communication Engineering

ISO 3297:2007 CertifiedImpact Factor 7.918Vol. 12, Issue 3, March 2023
DOI: 10.17148/IJARCCE.2023.12324
on our needs. Voice assistants' capabilities and advancements are always growing day by day to give users improved
performance. Our desktop-based voice assistant is built using Python modules and libraries, allowing it to function quickly
and efficiently on the desktop. The fundamental premise of our project is that the user asks the voice assistant to complete
their task using the device's microphone, and the command is subsequently translated into text. The text request is
processed after that, and a text response is provided along with any voice assistant work. In addition to fundamental daily
functions, we are attempting to integrate the idea of face identification for security purposes in our voice assistant to give
it more versatility and personality. Our application uses the fewest system resources, which decreases the need for
expensive systems and lessens the risk to your system because it doesn't communicate with servers directly.
There are many reasons that make this vocal voice command application necessary in practical settings. These are a few
of them: -
To make it possible for a very engaging user experience: Like no other interface, voice help keeps users' attention.
Users can ask for anything they want by speaking naturally to the programmes.
To eliminate user annoyance with the application: With the current machine system, we must touch, type, and use a
mouse to complete our task, which occasionally causes user frustration. Users can ask their desired task directly utilizing
a voice assistant.
Voice assistants are truly able to answer for each user: based on their location, language, and preferences. This
allows you to customize your app experience for each user.

III.TECHNOLOGY USED IN PERSONAL DESKTOP VOICE ASSISTANT

Users of the desktop voice assistant can provide voice commands to carry out a variety of tasks. The system must be able
to reliably recognise voice instructions, react quickly, and carry out the specified activities effectively.

Python: Python is a well-liked programming language for creating personal voice assistants on desktop computers. For
implementing speech recognition, natural language processing, and machine learning, it provides a number of libraries
and frameworks.

APIs for speech recognition: Google Cloud Speech-to-Text API, Amazon Transcribe, and Microsoft Azure Speech
Services are a few well-known speech recognition APIs. These APIs offer the ability to convert speech to text and can be
incorporated into voice assistant software.

Natural Language Processing (NLP) libraries: There are several NLP libraries available for Python such as Natural
Language Toolkit (NLTK), spaCy, and Stanford CoreNLP. These libraries help with tasks such as sentiment analysis,
named entity recognition, and part-of-speech tagging.

Text to Speech (TTS) engines: Popular TTS engines include Google Text-to-Speech, Amazon Polly, and Microsoft
Speech Services. These engines can be used to generate human-like speech output from text input.

Machine learning frameworks: Popular machine learning frameworks include TensorFlow, PyTorch, and Scikit-learn.
These frameworks can be used to train machine learning models for speech recognition and NLP tasks.

Graphical User Interface (GUI) libraries: GUI libraries such as PyQt and Tkinter can be used to create a visual interface
for the voice assistant application. The GUI can be used to display information such as weather updates, news articles,
and reminders.

Web APIs: Web APIs such as OpenWeatherMap, NewsAPI, and Spotify Web API can be used to integrate the voice
assistant with external services. These APIs allow the voice assistant to access weather forecasts, news articles, and music
streaming

Functional Requirements:
The desktop voice assistant should have the following functionalities:
• Wake word detection: The system should be able to detect a wake word such as "Hey, assistant" to activate
the assistant.
• Voice recognition: The system should be able to accurately recognize and interpret voice commands from the
user.
• Natural language processing: The system should be able to understand the user's intent and respond
accordingly.

© IJARCCE This work is licensed under a Creative Commons Attribution 4.0 International License 127
 IJARCCE ISSN (O) 2278-1021, ISSN (P) 2319-5940

International Journal of Advanced Research in Computer and Communication Engineering

ISO 3297:2007 CertifiedImpact Factor 7.918Vol. 12, Issue 3, March 2023
DOI: 10.17148/IJARCCE.2023.12324
• Task execution: The system should be able to execute tasks such as setting reminders, playing music, sending
emails, and searching the web.
• Multi-language support: The system should be able to recognize and interpret voice commands in multiple
languages.

Non-functional Requirements
The desktop voice assistant should meet the following quality attributes:
• Accuracy: The system should recognise voice commands with a high degree of accuracy.
• Speed of response: The system must react quickly to user commands.
• Security: The system must maintain user privacy and be secure.
• Usability: The system ought to be simple to operate and have an intuitive user interface.
• Constraints: Windows, Mac, and Linux operating systems should all be compatible with the desktop voice
assistant. Moreover, a variety of microphones and audio input devices should work with the system.
• For some operations, like sending emails and conducting web searches, the desktop voice assistant expects that
the user has a dependable internet connection. For several features like weather updates and music streaming, the system
also relies on third-party APIs.

Requirements:
1. Software Requirements:
• Windows OS.

2. Hardware Requirements:
• Minimum Requirement – 2 Gb RAM, Microphones.
• Recommended – 4 Gb RAM, Microphones.

Other Requirements:
● Internet Connection.

IV.RESEARCH METHODOLOGY
We are going to use python language and google text to speech API for this project, speech recognition module can be
used to recognize the voice of used, and based on its query will be fired. Many different modules i.e., web browser,
YouTube, Wikipedia, etc. are used to interact with the internet. the OS module is used to interact with operating system
related queries. For Learning purposes, users can search any information related to a certain topic on Wikipedia, Google
or in text documents. We are using some concepts related to AI and NLP for the processing of text into voice. Our
project's main goal is to develop a virtual voice assistant for blind people so they may use it to communicate with
emerging technologies, manage their devices, and learn from them.
V.Problem statement

Build a virtual voice assistant that will enable users to interact with emerging technologies, manage their devices, and
utilize technology for learning. It serves as a voice assistant for visually impaired people and is a cutting-edge system. By
utilizing distinct custom layouts and speech to text, this solution improves system quality while enabling visually
challenged users to access the desktop's most crucial functionalities. The user's speech will be the basis for all actions
taken by the system. The system assists the user based on voice note, meaning that it follows instructions provided by the
user. Because the user cannot see the action going place on the desktop, the system speaks out if the user needs to receive
a response.
• The blind applicant will also sense independence.
• Because the system is a machine, it will execute without error.
• Your smartphone will be controlled solely by voice commands, and the assistant will recognize the situation and
respond to the user appropriately.
• Although many seniors are unable to utilize desktop computers, they can still benefit from this.
These assistive technologies will enable users who are blind or visually handicapped to learn from, compete with, and
interact with their sighted counterparts.

VI.PROPOSED METHODOLOGY

© IJARCCE This work is licensed under a Creative Commons Attribution 4.0 International License 128
 IJARCCE ISSN (O) 2278-1021, ISSN (P) 2319-5940

International Journal of Advanced Research in Computer and Communication Engineering

ISO 3297:2007 CertifiedImpact Factor 7.918Vol. 12, Issue 3, March 2023
DOI: 10.17148/IJARCCE.2023.12324
• A personal desktop voice assistant is a software application that is designed to understand and respond to voice
commands provided by the user. The following is a high-level system design description for a personal desktop voice
assistant.

• User Interface: The user interface of the personal desktop voice assistant should be intuitive and easy to use. The
user should be able to interact with the voice assistant through natural language commands.

• Speech Recognition: The system should have a robust speech recognition module that can accurately convert
the user's voice commands into text. The speech recognition module should also be able to distinguish between different
users and adapt to their speech patterns.

• Natural Language Processing (NLP): The system should have an NLP module that can interpret the user's text
commands and extract the relevant information. The NLP module should also be able to identify the user's intent and
provide appropriate responses.

• Knowledge Base: The system should have a knowledge base that contains information on a wide range of topics.
The knowledge base should be regularly updated to ensure that the voice assistant can provide accurate and up-to-date
information.

• Machine Learning: The system should use machine learning algorithms to continuously improve its
performance. The machine learning algorithms can be used to improve speech recognition accuracy, NLP performance,
and user interaction.

• APIs: The system should be able to integrate with other applications and services through APIs. This will enable
the voice assistant to provide more comprehensive responses to user requests.

• Privacy and Security: The system should be designed to protect user privacy and ensure that user data is secure.
The system should only collect data that is necessary to provide the voice assistant's services, and user data should be
encrypted and stored securely.

• User Personalization: The system should be able to personalize the user experience based on the user's
preferences and previous interactions. The system should also be able to learn from user feedback and adapt to their
preferences over time.

• Action Fulfilment: Once the intent of the user's request is identified, the system will execute the necessary action.
For example, if the user requested to play a song, the system will find the song and play it through the desktop speakers.

• Response Generation: Finally, the system will generate a response to confirm that the requested action has been
completed. The response could be as simple as a confirmation message, or it could be more detailed, providing additional
information related to the user's request.

• Overall, a personal desktop voice assistant should be designed to provide a seamless and natural interaction
between the user and the system. The system should be reliable, accurate, and secure, and should continuously learn and
improve to provide better services to the user.

Workflow Diagram:

Wake word detection: The voice assistant is always listening for a specific wake word or phrase (e.g.,
"Hey Siri" or "Okay Google"). When the user says this wake word, the assistant wakes up and starts
listening for the user's request.

Speech recognition: The user speaks their request, which is then captured by the assistant's
microphone and converted to text using speech recognition technology.

© IJARCCE This work is licensed under a Creative Commons Attribution 4.0 International License 129
 IJARCCE ISSN (O) 2278-1021, ISSN (P) 2319-5940

International Journal of Advanced Research in Computer and Communication Engineering

ISO 3297:2007 CertifiedImpact Factor 7.918Vol. 12, Issue 3, March 2023
DOI: 10.17148/IJARCCE.2023.12324

Natural Language Understanding (NLU): The assistant analyses the user's request to understand the
intent behind it. This involves identifying the keywords and context of the request to determine the
user's desired action.

Intent mapping: The assistant maps the user's request to a specific action or set of actions. For
example, if the user asks "What's the weather like today?", the assistant would map this intent to a
weather app and retrieve the relevant information.

Action execution: The assistant executes the mapped action(s) and retrieves the requested
information, which is then presented to the user through text or speech.

Response generation: The assistant generates a response to the user's request, which is either spoken
aloud or displayed on the screen. This response may include the requested information, confirmation
of a completed action, or an error message if the assistant was unable to fulfill the request.

End of session: Once the assistant has provided a response, it goes back to "sleep" and waits for the
next wake word to begin a new session.

© IJARCCE This work is licensed under a Creative Commons Attribution 4.0 International License 130
 IJARCCE ISSN (O) 2278-1021, ISSN (P) 2319-5940

International Journal of Advanced Research in Computer and Communication Engineering

ISO 3297:2007 CertifiedImpact Factor 7.918Vol. 12, Issue 3, March 2023
DOI: 10.17148/IJARCCE.2023.12324

Use-Case Diagram:

The use case diagram shows the main interactions between the user and the personal voice assistant.
The user initiates the interactions by speaking to the assistant, which responds with the requested
information or action. The assistant is responsible for recognizing the user's speech, interpreting their
intent, executing the relevant action, and generating an appropriate response.

Some of the common use cases for a personal voice desktop assistant include asking for information,
setting reminders or appointments, sending emails, controlling home automation devices, playing
music, performing web searches, and checking the weather or news updates.
Sequence Diagram:

+-------------+ +------------------+
| User | | Voice Assistant |
+-------------+ +------------------+
| |
| Wake Word Detection |
|------------------------------>|
| |
| User's Request |
|------------------------------>|
| |
| Speech Recognition |
|<------------------------------|
| |
| Natural Language |
| Understanding |
|<------------------------------|
| |
| Intent Mapping |
|<------------------------------|
| |
| Action Execution |

© IJARCCE This work is licensed under a Creative Commons Attribution 4.0 International License 131
 IJARCCE ISSN (O) 2278-1021, ISSN (P) 2319-5940

International Journal of Advanced Research in Computer and Communication Engineering

ISO 3297:2007 CertifiedImpact Factor 7.918Vol. 12, Issue 3, March 2023
DOI: 10.17148/IJARCCE.2023.12324
|<------------------------------|
| |
| Generate Response |
|------------------------------>|
| |
| Speak Response |
|<------------------------------|
| |

The sequence diagram shows the interaction between the user and the voice assistant. When the user speaks the wake
word, the assistant wakes up and starts listening for the user's request. The user then speaks their request, which is captured
by the assistant's microphone and converted to text using speech recognition technology. The assistant analyses the user's
request to understand the intent behind it and maps it to a specific action or set of actions. The assistant then executes the
mapped action(s) and generates a response to the user's request. Finally, the assistant speaks the response to the user.

This sequence diagram illustrates the flow of communication between the user and the voice assistant and highlights the
key steps involved in processing the user's request.

Architecture Diagram:

+---------------------------------+
| Voice Assistant Service |
| (e.g., Alexa, Siri) |
+---------------------------------+
|
| 1. User's voice input
|
+---------------------------------+
| Speech Recognition API |
| (e.g., Google Cloud Speech) |
+---------------------------------+
|
| 2. Text output
|
+---------------------------------+
| Natural Language |
| Understanding API |
| (e.g., Dialog Flow, Wit.ai) |
+---------------------------------+
|
| 3. Intents and Entities
|
+---------------------------------+
| Personal Assistant |
| Logic and Responses |
+---------------------------------+
|
| 4. Actions and Responses
|
+---------------------------------+
| Desktop Application |
| (e.g., web browser, calendar) |
+---------------------------------+

Explanation of the components:

1. User's voice input: The user speaks to the personal desktop voice assistant, which captures the audio signal.

© IJARCCE This work is licensed under a Creative Commons Attribution 4.0 International License 132
 IJARCCE ISSN (O) 2278-1021, ISSN (P) 2319-5940

International Journal of Advanced Research in Computer and Communication Engineering

ISO 3297:2007 CertifiedImpact Factor 7.918Vol. 12, Issue 3, March 2023
DOI: 10.17148/IJARCCE.2023.12324
2. Speech Recognition API: The audio signal is then sent to a Speech Recognition API, which converts it into text.
3. Natural Language Understanding API: The text output from the Speech Recognition API is then sent to a Natural
Language Understanding API, which analyses the text and extracts intents and entities.
4. Personal Assistant Logic and Responses: Based on the intents and entities, the personal assistant logic and
responses are generated. These include actions and responses that the assistant can take, such as opening a web browser
or scheduling a meeting.
5. Desktop Application: Finally, the personal assistant interacts with the desktop application to perform the required
actions or provide the user with the requested information.

VII.IMPLEMENTATION

Several crucial processes may be involved in the Personal Desktop Voice Assistant deployment, such as:

• Python can access audio from your system's microphone, transcribing it, and save it thanks to the Speech
Recognition library.

• Using Google's text-to-speech software, or gTTS, your audio inquiries are converted to text. gTTS transforms
the response from the look-up function you write to retrieve the answer to the query into an audio phrase. The Google
Translates API is interfaced with via this package.

• Use the play sound package to give the response voice. Python's play sound function enables MP3 playback.

• Web browser software offers a high-level interface that enables users to view Web-based pages. Another choice
for showing web pages is Selenium. Nevertheless, you must install and supply the browser-specific web driver in order
to use this.

• The Wikipedia website is used to retrieve a range of information.

• Wolfram Alpha is a computational knowledge engine or answer engine that uses Wolfram's knowledge base and
AI technologies to compute mathematical questions. To use this package, you must fetch the API.

VIII.ADVANTAGES

Some advantages of Personal Desktop Voice Assistant include:

• Make up private conversations:
With voice assistants, marketers have a new opportunity to start conversations in a more personalised way. With voice
assistants, users typically express exactly what they want and are thinking. As a result, the channel enables marketers to
respond with what they require and then keep in touch with customers to provide a customised experience.

• Reach a large number of users at once:

Marketers can reach several consumers in a single home thanks to voice assistants. Because each of these customers has
different brand preferences, product interests, and music playlists, they all make distinctive purchasing judgements. One
voice assistant allows marketers to collect more data and sell through a single targeted campaign, resulting in better
outcomes.

• Beyond the typical tools

The fact that voice assistants are gaining popularity outside of our homes and mobile devices is an additional benefit.
They are becoming more prevalent in our automobiles, smart Televisions, wearable technology, and home appliances.
They offer fresh chances to accomplish even more goals while also giving current clients more value.

• Achieve elusive prospects

You have a better chance of reaching your target demographic by marketing via a virtual assistant on smartphones or
smart speakers. It provides you with an alternative to doing so to the Internet and mobile. Voicebot.ai estimates that 87.7
million American people currently use smart speakers, an increase of 32 percent from January 2019 and an increase of
85 percent.
IX.DISADVANTAGES

© IJARCCE This work is licensed under a Creative Commons Attribution 4.0 International License 133
 IJARCCE ISSN (O) 2278-1021, ISSN (P) 2319-5940

International Journal of Advanced Research in Computer and Communication Engineering

ISO 3297:2007 CertifiedImpact Factor 7.918Vol. 12, Issue 3, March 2023
DOI: 10.17148/IJARCCE.2023.12324
Some potential disadvantages Personal Desktop Voice Assistant of include:

• Concerns about data security

Despite the fact that people are using voice assistants more frequently, there is still a lot of worry about the information
these devices collect and the businesses that create the apps that run on them. Customers are concerned about the data's
storage methods, viewers, and eventual disposition. If marketers don't handle these data and privacy issues, they won't
be able to access these prospects or their data.

• Disconnected exchange
Another drawback is that compared to other platforms, voice assistants as a channel offer fewer enriching interactions.
The choices include visual interactions versus speech material alone, which generally means recycling current content.
This might make some of the more significant interactions that marketers can have elsewhere less effective.

• Reliance on gadget manufacturers

You are at the mercy of the manufacturers of devices, such as the corporations that build wearable tech, cars, and
appliances, as a marketer. Before getting started, you should carefully investigate the device manufacturers you wish to
collaborate with to achieve long-term success.

• Investing in voice-activated apps and skill sets

The cost of creating the voice app for this channel can be high. Building an internal skill set tailored towards the intricacies
of voice assistants may take a lot of time if you participate in this channel. Consequently, it's crucial to weigh the
advantages and disadvantages of using voice assistant channels.

X.CONCLUSION

In conclusion, personal desktop voice assistants are becoming increasingly popular as more people seek convenience and
efficiency in their daily tasks. With the development of advanced natural language processing and machine learning
technologies, these assistants can understand and respond to human queries in a more intuitive and human-like manner.

Personal desktop voice assistants have the potential to revolutionize the way we interact with our computers and devices,
making it easier to navigate and access information. They can also enhance productivity and provide entertainment
options, such as playing music or reading the news.

While personal desktop voice assistants have many benefits, there are also some concerns around privacy and security.
Users need to be aware of the data that is being collected and how it is being used to ensure their personal information is
protected.

Overall, personal desktop voice assistants have the potential to greatly enhance our daily lives and streamline our
interactions with technology. As technology continues to advance, it will be interesting to see how these assistants evolve
and improve in the years to come.

REFERENCES

[1]Palleti, V. (2021). SpeechRecognition. PyPI.

[2] Upadhyay, A. (2021). PyDictionary. PyPI.
[3] Sweigart, A. (2021). PyAutoGUI. PyPI.
[4] Yadav, M. (2021). pyttsx3. PyPI.
[5] Nallamothu, M., & Mukkamala, R. (2019). A Study on Speech Recognition and Desktop Assistant using Python.
Journal of Emerging Technologies and Innovative Research, 6(4), 521-526.
[6] Mukherjee, A. (2019). Survey on Virtual Assistant (Google Assistant, Siri, Cortana, Alexa). 4th International
Symposium SIRS 2018, Revised Selected Papers, 65-74.
[7] Haseeb, A., & Rizvi, S. A. R. (2022). A Review of Voice Assistant and Its Impact on the Healthcare Industry.
International Research Journal of Engineering and Technology, 9(1), 299-303.
[8] Oracle. (2018). Advantages and Disadvantages of Voice Assistants for Marketers. Oracle Marketing Cloud Blog.
[9] Muneer, S., & Khan, F. A. (2022). Artificial Intelligence and Its Applications in Healthcare. International Research
Journal of Modernization in Engineering, Technology and Science, 1(4), 23-27.

© IJARCCE This work is licensed under a Creative Commons Attribution 4.0 International License 134
 IJARCCE ISSN (O) 2278-1021, ISSN (P) 2319-5940

International Journal of Advanced Research in Computer and Communication Engineering

ISO 3297:2007 CertifiedImpact Factor 7.918Vol. 12, Issue 3, March 2023
DOI: 10.17148/IJARCCE.2023.12324
[10] Tripathy, S. (2020). Build Your Own Desktop Voice Assistant in Python. Analytics Vidhya.
[11] Kumar, A., Kumar, A., & Kumar, P. (2021). Development of Voice Assistant using Python. International Journal of
Research in Engineering and Science, 10(2), 43-50.
[12] GitHub. (n.d.). Topics - desktop-assistant.

© IJARCCE This work is licensed under a Creative Commons Attribution 4.0 International License 135