Abstract

Today, technological advancement is increasing day by day. Before, there was only a computer system in which we could do a few tasks. But now machine learning, artificial intelligence, deep learning, and several other technologies have made computer systems so advanced that we can perform any type of task. In such an era of progress, if people are still struggling to interact with different input devices, then it's not worth it. For this reason, we have developed a voice assistant using python that allows the user to run any type of command in windows without interacting with the keyboard. The main task of a voice assistant is to minimize the use of input devices such as a keyboard, mouse, etc. It will also reduce hardware space and cost.

Introduction

 In this technological era, everything that man can do is replaced by machines. One of the main reasons is the performance change. In today's world, we train our machines to think like humans and do its task by themselves. That's why the concept of a virtual assistant came about.

A virtual assistant is a digital assistant that uses voice recognition functions and language processing algorithms to recognize the user's voice commands and perform the relevant tasks according to the user's requests. Based on specific commands given by the user, the virtual assistant is able to filter out ambient noise and return relevant information.

Virtual assistants are completely software, but these days they are integrated into various devices, and also some assistants are designed specifically for individual devices, such as Alexa. Due to drastic changes in technology, now is a. high time to train our machine using machine learning, deep learning, neural networks. Today, we can talk to our machine using a voice assistant. Today, every big company uses Voice Assistant so that their user can take help from the machine through their voice. So with the voice assistant, we're taking it to the next level where we're able to talk to our machine. 

Why use a Voice Assistant

These types of virtual assistants are especially useful for the elderly, blind and physically challenged people, children, etc., as they ensure that interaction with the machine is no longer a challenge for humans. Even blind people who have not seen the machine can communicate with it using only their voice.

Here are some of the basic tasks that can be done with the help of voice assistant: -

• Getting news updates

• Getting updates on mail

• Search on the web

• Play music or video

• Setting a reminder

• Run any program or application

• Getting weather updates

These are some of the examples, we can do many more things according to our requirements. The voice assistant we have developed is a desktop-based built using python modules and libraries. This assistant is just a basic version that could perform all the basic tasks which have been mentioned above, but the current technology is although good in it is still to be merged with Machine Learning and IoT for better enhancements.

About the Project

The voice assistant developed by us is for Windows users. This voice module is desktop based which is built using python modules and libraries. It is a basic version that can perform all the basic daily task assigned to them by the user operating it. Some of the tasks to be performed by our assistant are listed above. Current technology is good in many ways, but it can still be improved by merging with machine learning and the Internet of Things (IoT). We used Python modules and libraries along with artificial intelligence and machine learning to train our model. Some Windows commands have also been used in our model to make it run smoothly on the Windows operating system.

We have also added a few health features like:

·       Sending reminders to people to take their medicines via WhatsApp

·       Getting analysis of your blood pressure based on user input

·       Also know about your diabetes from user input

It can be used according to the user's requirement. Machine learning and deep learning along with natural language processing concepts help us achieve our goal and accomplish the desired task. With an assistant, we don't have to type a command over and over again to perform a specific task. Once the model is created, it can easily be used by any number of users. Basically, we can control many things on a single platform with this virtual assistant.

Existing Models

Some of the existing Voice Assistants:-

• ALEXA - Amazon launched the Amazon Echo in 2014. This ‘smart speaker’ introduced consumers to the voice assistant Alexa which was designed in-house. The Echo was a way for Amazon to establish a presence in the home. Securing and building upon this presence in the home could be a key strategy for Amazon to develop its members base and further increase revenue
• SIRI - Siri was originally acquired by Apple in 2010 for an estimated 100-250 million USD. It is arguably the most well-known voice assistant thanks to an earlier launch than its competitors, availability in more languages, and native support in many Apple devices, including iPhones.
• GOOGLE ASSISTANT - Google Assistant is Google’s voice assistant available on smartphones and smart home devices. Launched in 2016, Google Assistant has spread quite far as it is not only available on its own products but a huge range of devices through partnerships with other companies.  

Few of the techniques used by them are-

• Context-Aware Computing
• Mel-Frequency Cepstral Computing
• Natural Language Processing

Proposed System

Speech to text:

 A piece of software is used that converts audio to text. They don't understand anything you might say.

Text Analysis:

 The converted text is only computer letters.

 A piece of software converts text into something the computer can understand.

 The computer understands the command, so virtual assistants like Siri translate that text into a computer command.

 VPAs map words to functions and parameters and produce a command that the computer understands.

 

WORKING PRINCIPALS

The working of a Virtual Assistant uses the following principles:

1.   Natural Language Processing: Natural Language Processing (NLP) refers to an AI approach to intelligent programming using a natural language such as English

2.     Automatic Speech Recognition: To understand commands according to the user’s input.

3.  Artificial Intelligence: To learn things from the users and to store all information about the behavior and relations of users.

OUTPUT