1

PERSONAL VOICE
ASSISTANT IN
PYTHON
Submitted By:
Rahul R
Ivin KR
Sourav Raj P P
Ashin Thankachan
Arunrag C
Contents 2

 Introduction
 How does an intelligent personal assistant work?
 Existing system and proposed system
 Dataflow diagrams
 Automatic Speech Recognition System Model in Google AP
 Use case diagrams
 Modules
 screenshots
 Requirements
 Conclusion
Introduction 3

 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 exciting thing happens between these two
actions.
 It is a combination of several different technologies: voice recognition, voice
analysis and language processing.
 It is completely developed using one of the most powerful language python.
How does an intelligent personal assistant 4

work?
 User asks a personal assistant to perform a task.
 The natural language audio signal is converted into digital data that can be
analyzed by the software.
 Compared with a database of the software using an innovative algorithm to find a
suitable answer.
 This database is located on distributed servers in cloud networks. For this reason
,it must have a reliable Internet connection.
 EXISTING SYSTEM V/S PROPOSED SYSTEM 5
Existing System Proposed System

Usage statistics and user data are sent to the Does not collect any user data
developer

Installation required Installation required

User cannot edit or change the modules User can edit and add new modules

Not a free Software Free Software

lightweight

Simple User interface

Dataflow Diagrams 6

DFD - 0

Personal
Voice Speech to Action
User voice Computer
Text
assistant

Response

Voice output
Text to speech
 7
DFD - 1

Personal voice
assistant
Voice Command Perform action
User Voice to text Computer
Action perform
Database
 8
DFD - 2

Microphone Google voice API

Flow sensor Voice audio

User This will convert
This will convert
value data voice data into text
voice into binary
form

Perform action

Computer
 Automatic Speech Recognition System Model in 9
Google API

Acoustic Pronunciation Language

models Dictionary Models

Speech signal Recognized words

Feature Extraction Decoder
 Feature Extraction 10

 Feature Extraction is a common to extract a set of features from speech signal.

 Classification of Feature extraction is carried out on the set of features instead of
the speech signals themselves.
 The feature extraction stage seeks to provide a compact representation of the
speech waveform. This form should minimize the loss of information that
discriminates between words, and provide a good match with the distributional
assumptions made by the acoustic models.
 ACOUSTIC MODELS 11
• Acoustic model is a relationship between audio signal and phoneme
• Phoneme means one of the smallest unit of speech that make one word different from another word
 PRONUNCIATION DICTIONARY
• The act or result of producing the sounds of speech, including articulation, stress, and intonation
• A phonetic transcription of a given word, sound, etc.
• An accepted standard of the sound and stress patterns of a word, phrase, etc.
 LANGUAGE MODELS
• The language model provides context to distinguish between words and phrases that sound similar.
for example, In American English the phrases “recognize speach” and “wreck a nice beach” sound
similar , but mean different things.
Use case diagrams arc
h 12
Se
Turn
n n ew

nder
Sent e
Op b

Ap los and
on/off

Set
ta

s
ion
mail

Remi

pli e
Wi Fi

en
ery

cat
t

Op
t
Ba nfo

c
i
eb er
W ws
o
br e
Tak shots
c reen
s
Input Read
voice Wikipedia search

User t op

Ask
Music
Play /S

Time
User Microphone Computer Google API 13
Open Personal Assistant Accessing G-API

Voice response

Start Mic

Wait until user speak

Receive data
Convert audio to text

Match text with action

Perform action

Voice / Text
Response
 MODULES 14

 Speech recognition

 Process and system utilities ( psutil )

 PlaySound

 SMTP Protocol client ( smtplib )

 Google Text To Speech ( gtts )

 15

SCREENSHOTS
Eva Installation 16
17
18
19
20
21
22
User Interface 23
24
25
26
27
Requirements 28

 Software requirements
 Pycharm IDE/visual studio code
 Inno Setup Compiler
 Pyinstaller
 Python 3.8.2 and its Sub modules

 Hardware requirements
 Intel core i3
 4gb RAM
 30 Gb Hard drive space
Conclusion 29

Voice Controlled Personal Assistant System will use the Natural language processing
and can be integrated with artificial intelligence techniques to achieve a smart
assistant that can control the computer and applications and even solve user queries
using web searches.. It can be designed to minimize the human efforts to interact with
many other subsystems, which would otherwise have to be performed manually. By
achieving this, the system will make human life comfortable
 30

THANK YOU