Virtual Assistant

PROJECT

BACHELOR OF
TECHNOLOGY
CSE

DEPARTMENT OF COMPUTER SCIENCE AND

ENGINEERING
Chandigarh Engineering College –Landran
Mohali, Punjab - 140307
December 2021

SUBMITTED BY -
Santanu dass (2002618)
Rashau rani (2002587)
Divyanshi grover (2002423)
Deepanshu gupta (2002410)
S.no

INDEX
1

INTRODUCTION

METHODOLOGY
3

OUTPUT
 1. INTRODUCTION

A virtual assistant is a technology based on

artificial intelligence.The software uses a
device’s microphone to receive voice requests
while the voice output takes place at the speaker.
But the most excitingthing happens between
these two actions.

In the present times, we all are familiar with virtual

assistants. We all have virtual assistant in our smartphones
which are capable of doing some great things like just by
saying “OK GOOGLE” (in android) or “HEY SIRI” (in
ios) we can do searches on internet, set a reminder, call
someone and may more things.
.

Alexa

Alexa, Amazon's virtual assistant, is built into the Amazon Echo line of smart speakers. You can
also find it on some third-party speakers from brands like Sonos. You can ask the Echo questions
like, "Alexa, who is hosting SNL this week?" You can also ask it to play a song, make a phone call,
or control your smart home devices. It has a feature called "multi-room music," which lets you play
the same tunes from each of your Echo speakers.
Alexa recognizes a handful of wake words, including "Alexa," "Amazon," "Computer," "Echo,"
and "Ziggy."

You can also configure the Amazon Echo with third-party apps, so you can use it to call an Uber,
pull up a recipe, or lead you through a workout.
 Bixby

Samsung's take on virtual assistants is Bixby, which is compatible with Samsung

smartphones with Android 7.9 Nougat or higher. Like Alexa, Bixby responds to voice commands.
It can give you reminders about upcoming events or tasks. It can control most of your device
settings and can mirror content from your phone to most Samsung Smart TVs.
You can use Bixby along with your camera to shop, get a translation, read QR codes, and identify
a location. For example, you can take a picture of a building to get information about it or snap a
photo of a product you want to buy. You can also take a photo of text you want translated.

Google Assistant

Google Assistant is available on many Android phones, including Google Pixel smartphones, as
well as the Google Home smart speaker, and some third-party speakers from brands including
JBL. You can even set it up on an iPhone.

You can interact with Google Assistant on your smartwatch, laptop, and TV. While you can use
specific voice commands, it also responds to a conversational tone and follow-up questions.
Google Assistant interacts with a multitude of apps and smart home devices.
 Siri

Siri, perhaps the most well-known virtual

assistant, is Apple's brainchild. This virtual
assistant works on iPhone, iPad, Mac, Apple
Watch, Apple TV, and HomePod, the company's
smart speaker.

The default voice is female, but you can change it to

male, and change the language to Spanish, Chinese,
French, and many others. You can also teach it how
to pronounce names correctly. When dictating, you
can speak out the punctuation and tap to edit if Siri
gets the message wrong. For commands, you can use
natural language.
 . METHODOLOGY

Speech Recognition module

The system uses Google’s online speech recognition system
for converting speech input to text. The speech input Users
can obtain texts from the special corpora organized on the
computer network server at the information centre from the
microphone is temporarily stored in the system which is
then sent to Google cloud for speech recognition. The
equivalent text is then received and fed to the central
processor.

Python Backend:
The python backend gets the output from the speech
recognition module and then identifies whether the
command or the speech output is an API Call and Context
Extraction. The output is then sent back to the python
backend to give the required output to the user.
API calls
API stands for Application Programming Interface. An
API is a software intermediary that allows two
applications to talk to each other. In other words, an API
is a messenger that delivers your request to the provider
that you’re requesting it from and then delivers the
response back to you.

Content Extraction
Context extraction (CE) is the task of automatically
extracting structured information from unstructured
and/or semi-structured machine-readable documents. In
most cases, this activity concerns processing human
language texts using natural language processing (NLP).
Recent activities in multimedia document processing like
automatic annotation and content extraction out of
images/audio/video could be seen as context extraction
TEST RESULTS.

Text-to-speech module
Text-to-Speech (TTS) refers to the ability of computers to
read text aloud. A TTS Engine converts written text to a
phonemic representation, then converts the phonemic
representation to waveforms that can be output as sound.
TTS engines with different languages, dialects and
specialized vocabularies are available through third-party
publishers.
Features of virtual assistant:

It can send emails on your behalf.

It can play music for you.
It can do Wikipedia searches for you.
It is capable of opening websites like Google,
Youtube etc., in a web browser.
It is capable of opening your code editor or IDE with
a single voice command.
. OUTPUT:
It opens youtube.

It opens google.
It opens music list.

It opens Wikipedia.