Sie sind auf Seite 1von 9

ABSTRACT :

Who doesn't want to have the luxury to own an assistant


who always listens for your call, anticipates your every need, and takes
action when necessary? That luxury is now available thanks to artificial
intelligence-based voice assistants.

A Desktop voice assistant is a program that can perform


tasks or services for an individual based on verbal commands i.e. by
interpreting human speech and respond via synthesized voices. Users can
ask their assistants’ questions, control home automation devices, and
media playback via voice, and manage other basic tasks such as email,
to-do lists, open or close any application etc with verbal commands.

Voice assistants come in somewhat small packages and


can perform a variety of actions after hearing your command. They can
answer questions, play music, place online orders and do all kinds of
AI-based stuff.
INTRODUCTION:

What is Desktop Voice Assistant ?

 Concept of artificial personal assistant

 Voice controlled Personal Digital Assistants

The combination of :

a)Automatic Speech Recognition

b)Artificial Intelligence

c)Natural Language Processing

d)Inter Process Communication

 Natural Language Processing :

- To Understand user’s speech input

 Automatic Speech Recognition:

- To understand command according to user’s input

 Artificial Intelligence:

- To learn things from user and to store all

information bout behavior and relations of user

 Inter Process Communication:

- To get important information from

other software applications


SYSTEM REQUIREMENTS:

 Pc with Windows Operating System


 Window s 7,8,8.1 or 10
 4Gb RAM
 100 Mb of free space on hard drive
 Internet Connectivity
 Support of other basic applications like maps,camera,web connection
etc.,

Domain :

With the role and the target user group in mind, we can create
a better understanding of the domain. This helps to anticipate the voice
input the assistant will receive and provides insights on expectations. This
includes not just expectations for functionality, but also for the tone of
voice and the behavior of the assistant. What questions help to guide this
process and what data can be leveraged?
Runtime :

Windows Speech Recognition (WSR) is a speech


recognition component developed by Microsoft for the Windows
Vista operating system that enables the use of voice commands to
control the desktop user interface; dictate text in electronic
documents and email; navigate websites; perform keyboard shortcuts;
and to operate the mouse cursor. It also supports the creation of
custom macros to perform additional tasks.

WSR is a locally-processed speech recognition platform; it does


not rely on cloud computing for accuracy, dictation, or recognition, but
adapts based on a user context, grammar, input, speech samples, training
sessions, and vocabulary. For dictation, it provides a personal dictionary
that allows users to include or exclude words or expressions and to
optionally record pronunciations to increase recognition accuracy.
With Windows Search,WSR can also optionally analyze and collect text in
documents, email, and handwritten input on a tablet PC to contextualize
and disambiguate terms to further adapt and personalize the
recognizer.[2] Custom language models that adapt the recognizer to the
specific context, phonetics, and terminology of users in particular
occupational fields such as legal or medical are also supported.[3]
Desktop voice assistant using python:

I thought it would be cool to create a personal assistant in Python.


If you are into movies you may have heard of Jarvis, an A.I. based
character in the Iron Man films. In this tutorial we will create a robot.

The features I want to have are:

 Recognize spoken voice (Speech recognition)


 Answer in spoken voice (Text to speech)
 Answer simple commands

 Recognize spoken voice(speech recognition):

Speech recognition can by done using the Python


SpeechRecognition module. We make use of the Google Speech
API because of it’s great quality.

 Answer in spoken voice (Text To Speech)

Various APIs and programs are available for text to speech


applications. Espeak and pyttsx work out of the box but sound very
robotic. We decided to go with the Google Text To Speech API, gTTS.

sudo pip install gTTS

Using it is as simple as:

from gtts import gTTS


import os
tts = gTTS(text='Hello World', lang='en')
tts.save("hello.mp3")
os.system("mpg321 hello.mp3")

Our next step is to create multiple if statements corresponding to


each of the features. So let us see how to create these small modules
inside if statement for each command:

1. Open any website in the browser:

You can open any website just be saying “open website.com” or


“open website.org”.
For example: “Please open facebook.com” or “Hey, can you open
linkedin.com” like this you can ask Sofia to open any website for you.

2. Send Email:

You can also ask your desktop assistant to send the email.

How it works : If you have said the word email in your


command then the bot will ask for receipient, If my response
is rajat, the bot will use pthons smtplib library. The smtplib
module defines an SMTP client session object that can be
used to send mail to any Internet machine with an SMTP or
ESMTP listener daemon. Sending mail is done with Python’s
smtplib using an SMTP server. First it will initaite gmail SMTP
using smtplib.SMTP(), then identify the server
using ehlo() function, then encypting the
session starttls(), then login to your mailbox using login(),
then sending the message using sendmail().
3. Launch any system application:

Say “launch calendar” or “can you please launch skype” or “Sofia


launch finder” etc. and Sofia will launch that system application for you.

4.Tells you the current weather and temperature of almost any city:

Sofia can also tell you the weather, maximum and minimum
temperature of any city around the world. The user just needs to say
something like “what is the current weather in London” or “tell me the
current weather in Chennai”.

5.Tells you the current time:

“Sofia can you tell me the current time ?” or “what is the time now ?” and
Sofia will tell you the current time of your timezone.

6.Greetings/ leave:

Say “ hello Sofia” to greet your voice assistant or when you want the
program to terminate say something like “shutdown Sofia” or “Sofia
please shutdown” etc.

7.Play you a song on VLC media player:

This feature allows your voice bot to play your desired song in VLC
media player. The user will say “Sofia play me a song”, the bot will ask
“What song shall I play Sir?”. Just say the name of the song and Sofia will
download the song from youtube in your local drive, play that song on the
VLC media player and if you again play a song the previously downloaded
song will get deleted automatically.
8. Change desktop wallpaper:

You guys can also change your desktop wallpaper using this feature.
When you say something like “change wallpaper” or “Sofia please change
wallpaper” the bot will download random wallpaper from unsplash.com
and sets it as your desktop background.

9.Tells you latest news feeds:

Sofia can also tell you the latest news update. The user just has
to say “Sofia what are the top news for today ?” or “tell me the news for
today”.

10.Tells you about almost anything you ask:

This bot can fetch details of almost anything you ask her. Like “Sofia tell
me about Google” or “Please tell me about Supercomputers” or “please
tell me about the Internet”. So as you can see you can ask about almost
anything.

Let’s start building our desktop voice assistant


using python:

Das könnte Ihnen auch gefallen