Design and Construction of Voice Activation Control Project (1 & 2) - For Merge (1) (Repaired) (Repaired) (Repaired)
Design and Construction of Voice Activation Control Project (1 & 2) - For Merge (1) (Repaired) (Repaired) (Repaired)
By
ELECTRICAL/ELECTRONIC ENGINEERING
EBONYI STATE
SUPERVISOR:
ENGR. OGECHI
DECLARATION
I,ONYEAGBA PRINCEWILL CHIKE hereby declare that this work, DESIGN AND CONSTRUCTION
VOICE ACTIVATION CONTROL SYTEM, is the product of my own research efforts, undertaken
under the supervision of Engr Ogechi and has not been presented elsewhere for the award of a degree.
__________________________________
2017/EN/4620
CERTIFICATION
It is hereby certified that this research project titled DESIGN AND CONSTRUCTION OF VOICE
ACTIVATION CONTROL SYSTEM, is an original work conducted, carried out and written by
fulfillment of the requirements for the award of Bachelor of Engineering (B.ENG) degree in the
Ndufu Alike.
___________________ __________________
Supervisor
___________________________________
Head of Department
___________________ __________________
External Supervisor
DEDICATION
I dedicate this work to God Almighty for the gift of privilege and opportunity and I will also like to
My profound gratitude goes to my Supervisor and Head of Department, Engr Ogechil, for his love,
professional and insightful advice, and for his support that helped me enormously throughout this
journey. Indeed, he was very instrumental to the success of this project. I could not have had a
better supervisor.
In a special way, I wish to appreciate the love, prayers and support of my parents, friends and
System Automation is fast becoming a trending research area in the 21st century considering its
great importance in every aspect of our daily lives. This report is mainly based on the design and
construction of voice automation control which is one of the most important applications of system
automation. Looking into the advancement in technology, there is an incessant need for smarter
homes and that is why this project is important. It incorporates not only voice as a biometric
activator but, it also integrates a wireless connection between voice and the automaton control
system. This project is also special because it has been designed in such a manner that a voice
recognition system can be as far as over 1 kilometer away from the home automation system to
automate any appliance connected to it which is communicated through a wireless medium. This
projection was brought into fruition by means of extensive programming, in depth researches,
guidance and opinions from my supervisors as well as colleagues through various evaluation
processes. The very basics of this project are so that this system can enable the users have absolute
control over most appliances in their homes using their voices The control circuit which consists of
an Arduino uno microcontroller processes the users voice commands via an android Smartphone
which is installed with ‘AMR voice’ interface. A relay controls the switching of appliances via a
wireless HC-05 Bluetooth module, which shares a signal data between the microcontroller and the
Android phone.
CHAPTER ONE
INTRODUCTION
The rate at which technology is advancing is a thing of marvel and through the continuous
monumental advancements in fields such as wireless communication and information technology
(IT), it is now more than ever, very possible to integrate various aspects of smartness into our
homes.
The use of infrared controlled units like the remote control used in operating home appliances such
as the central air conditioning units, heating and lighting systems and so many others are on the
rapid increase due to its ease of use and comfort.
This system majorly provides better control locally and remotely, improving usability and
functionality of any home it is installed in, enabling savings on cost and power. This project
demonstrates a system that can be integrated as a single portable unit and allows the users to
wirelessly control their home appliances/devices by turning them ON/OFF accordingly. The voice
command conveyed to the control unit is converted into binary sequence by an Arduino uno
microcontroller which switches the load ON/OFF as desired. The microcontroller unit takes
commands and performs the required task.
The methods adopted are the use of two systems, with one handling the voice recognition and
sending the results wirelessly to the other system handling the home automation. All steps and
procedures used to arrive at this will be explained in later reports.
PROJECT BACKGROUND
The term automation was coined in the automobile industry in 1946 to describe the increased use
of automatic devices and control in mechanized production lines. The origin of the word is
attributed to D.S Harder, an engineering manager at the ford motor company at the time. The word
is used widely in manufacturing context, but it is also applied outside manufacturing in connection
with a variety of systems in which there is a significant substitution of mechanical, electrical or
computerized action human effort or intelligence.
Therefore, automation can be defined as a technology concerned with performing a process by
means of programmed commands combined with automatic feedback control to ensure proper
execution of the instructions (Britannica). Automation according Wikipedia, describes a wide
range of technologies that reduce human intervention in process, namely by predetermining
decision criteria, sub-process relationships, and related actions as well as embodying those
predeterminations in machines.
Automation has been achieved by various means including mechanical, electrical, electronic
devices and computers, usually in combination. The benefit of automation includes labor savings,
reducing wastes, Savings in electrical cost, Improvements to quality, accuracy and precision. In the
simplest type of an automatic control loop, a controller compares a measured value of a process
with a desired set value and processes the resulting error signal to change some input to the
process, in such a way that the process stays at its set point despite disturbances.
With this brief detailed background on automation, it can be postulated that home automation in
the this sense is the technology concerned with the performance of a home by means of
programmed instructions linking with automatic results to ensure concise execution of the these
programmed instructions (Somfy team, 2018). Home automation or domestics is the process of
building or installing automation for a home, which in this context is coined as a smart home or a
smart house. A home automation system will monitor and control home attributes such as lighting,
climate condition, and Entertainment systems. It may also include home security such as access
control and alarm systems. When connected with the internet, home devices are an important
constituent of internet of things IOT (Wikipedia).
In 1975, the first general purpose home automation network technology, X10 was developed as a
connection protocol for electronic devices. It primarily uses electric power or transmission wiring
for signaling and control when the signals involve brief radio frequency bursts of digital data and
remains the most widely available. By 2012, in the United States, according to ABI research, 1.5
million home automation systems were installed. And by the end of 2018 more than 45 million
smart home devices must have been installed in the U.S homes (Statista).
Now taking a brief outlook into the realm of voice automation control, the road to speech
recognition began with a system named Audrey, created by bell laboratories in 1952. As of then
Audrey was fairly rudimentary, as it was only capable of understanding numbers spoken by
specific people. A decade later, IBM’S shoebox machine, which could understand 16 words
spoken only in English by a designated speaker, was invented. These caveats proved to be
problematic and only increased skeptics opposing voice recognition.
From the 1950’s onward, there were numerous approaches to speech recognition that did little to
advance the technology. However, in the early 1980’s came the Hidden Markov Model (HMM).
The HMM drastically altered the development of a viable speech recognition software by way of
HMM, speech recognition went from using templates to understanding words to as statistical
method that measured the probability of unknown sounds being words to go from a few hundred to
a few thousand. Thus, the potential to recognize an unlimited number of words was in the horizon.
After multiple attempts to successfully launch this technology it didn’t generate much market
appeal until late 2010, where finally made into the hands of the masses.
Apple successfully implemented the voice activation technology on the very first Iphone, which
prompted Google to release a voice search app to its Smartphone soon after.
Now taking into consideration the afore mentioned background study, it can finally be deduced
from an empirical stand point, how this project has been technically observed and extensively
matched to result in the very first useful outcome, which is voice automation control.
STATEMENT OF PROBLEM
In the present day, robotics is swiftly but, imminently becoming a forerunner in the advancement
of our living conditions. The voice automation control system offers a diverse and advanced
method of controlling and communicating with our home appliances and devices. A home is for
many, a bane of sanctuary and refuge, and since human wants are insatiable, comfort must be
improved to keep up with the growing demands. In order to meet this standard, smartness must be
integrated into homes. Many research works have been carried out in this area, however there has
been no clarity as regards the circuitry and schematic diagrams of systems in the literature as well
as coding of the Arduino microcontroller for comprehensive understanding.
SIGNIFICANCE OF STUDY
The voice activated home automation system will help to control different loads (electrical
appliances) with simple voice commands centrally granting single-point control to the low-down
on all home functions
Project attempts to implement a system that will overcome the disadvantages of traditional system
in speech recognition base on the controlling of home appliances.
The aim of this project is to design and implement (prototype testing) a smartness of voice
Interactions for home automation done wirelessly for a switch ON/OFF of the electrical
To activate a communication between an android phone device and the Bluetooth enabled
micro-controller wirelessly.
Eradicate conventional switches and ease up living conditions.
Design an interface for a Bluetooth module and a microprocessor module.
Smart phone will be used for the application software which will connected to Google
Voice command input.
This project is only for voice control and home appliances, taking “ON” and “OFF” voice
Commands through application software connected to the Google voice command input in
Smartphone for automation.
It consists of Arduino uno microcontroller which interprets user instructions and manages device
switching. Bluetooth module uses wireless technology for data transfer, establishes the connection
between the microprocessor and a Smartphone for automation of home appliances (bulbs, socket
and others)
CHAPTER 2
LITERATURE REVIEW
Voice recognition often times called speaker recognition has incorporated a wide range of fields,
both in the method of recognition and applications. (Shrutijoshi, March 2017) proposed voice
recognition as a system which detects human voice, converts/reforms it into signals for
understanding machines at the point of application. (Sourav De, January 2014) described voice
recognition as a three step process, first labeled training where processed voices are stored in the
system for future referencing, the second labeled training where stored processed voices and
processed voices are compared, lastly results are when a match comes up, the application is set to
play and if there isn’t a match the system disapproves the application.
(Barbu, July 2009) proposed voice recognition into two forms which are; Text (speech) dependent
voice recognition, disapproving speakers on the basis of the same speech and text (speech)
independent voice recognition, disapproving speakers on the basis of any speech, where the text
dependent is applying a DDFMC based feature extraction while the text independent will be
applying techniques like vector quantization or Gaussian mixture models which area are the most
reliable.
(Muniz, 2007) postulated a complex voice recognition system with in depth analysis dividing the
system into subsystems, subunits, mentioning the subsystems done audio processing system which
gathers and processes the audio in play. Distance processor subsystem allows the audio processing
at the same time interval, operation subsystem where the new audio can be added to the database
or a user can be identified. Control unit subsystem indicates the states of the whole system by
controlling the LED lights, the Add, identify and validation subsystem are constraints of the
control unit subsystem, memory subsystem to store and read the features of the voice input.
Action register subsystem receives the synchronized user input, also sends action to the control
unit when system is idle via action signal and finally, the VGA (Video Graphics Array) subsystem
which produces the horizontal, vertical sync and blanking signals also produce pixels and line
count
RELATED WORKS
(AwadallaTaifor Ali, April 2007) and (Gayatri R, Shinde, July 2015) maneuvered using a wireless
channel (RF modules) which is an exemplary idea but still voice commands are trained and on the
easy VR 2.0 voice recognition utilizing software “Easy VR Commander” but (GayatriR.Shinde,
July 2015) used a v3 recognition module and added a keypad for a non-voice controlled
automation. The two projects give an option of registering any custom voice command and then
training the module to recognize the command. Also, that voice command can be tested for an
accurate recognition by speaking it in the microphone and then the software indicates the
command spoken on the screen. This software also has a key feature of generating an Arduino-
Based code depending on the number of voice commands trained, which is compatible with
“Energia”. Here the software “Energia” is used to program the Arduino uno development board,
which contains the Atmega328-IC [6-8]. In conclusion, in this project the preliminary test results
are promising.
(Marlon Jose, 2015)procured a project on the development of a voice command system as the
offline Google Speech Recognition Engine taking care of the recognition part. The system’s user
intermediary is a cell phone Android Application, which sends instruction also to an Arduino
board to execute the commands. In conclusion of the project sometimes, the Google Speech
Recognition was not able to recognize the speech. Therefore, that opens up the opinion that this
tool is not fully reliable, and further development of a more reliable speech recognition tool should
be considered.
(Kuilay Tasdelen, April 2018) made audio controlled home automation possible with easy VR
Microphone, sounds are detected through the use of the card/module, the easy VR commander is
then tasked with the program, the result of this comparison is to determine the Arduino Uno
decision in giving out the instruction to the relay card, when the switch provides the necessary
control. In conclusion, the performance and efficiency of the project changing from time to time
due to differences in voice resounding. As regards the use of the microcontroller, a more portable
and cheaper one could have been used like the Arduino uno to save cost and space for the device,
also the use of direct communication to the device in a wide range without a secure channel as to
(Rahul Deokar, June 2019), proving a voice-controlled home automation system could be
incorporated with an Atmega328p instead of an Arduino board where the voice commands given
by the user via AMR Application which converts voice to electrical signal is transferred by
Bluetooth to the microcontroller which detects the voice commands and the proceeds with
switching accordingly.
home automation system) is introduced to be a more compatible and comfortable voice automation
technology. VCHAS incorporated a transducer, keyboard, integrated circuit for speech recognition,
RF module, and AVR microcontroller primarily. Additional equipments such as the LCD Is
commonly added to develop the home automation systems capabilities and make it more user-
friendly.
(Jinn-KweiGuo, September 2009) was interested in the replacement of the conventional control
unit in the ZigBee network. He developed a hand-held interactive voice controller instead of the
LCD and the keyboard, due to the limitation of BSR library implemented, because only 5 speech
words could be recognized. Due to the limited recognition capability provided by their provider is
extended by the multi-stage algorithm. This shows some scalability and feasibility in our
algorithm.
(Sharma, May-June 2013) procured an overall system controlled from a microphone which is
connected with HM 2007nspeech recognition chip. This chip sends the voice command in binary
sequence to microcontroller. The base station unit then takes decision and sends the commands to
remote station by ZigBee transceiver. The remote system receives the commands through ZigBee
transducer and performs the request function. The sensors unit is able to detect when the user
leaves the room by measuring the change in signal strength between the access points and can
accordingly turn off appliances such as electric bulbs and fans and in the meantime sends its status
back to the base station, the inclusion of this unit has made this project unique and exemplary.
(HumaidAlshu’eili, May 2011) brought about a system which implements Automatic Speech
Recognition engines through Microsoft Speech API’s. The system applies the wireless network
using ZigBee RF modules for their efficiency and low power consumption. Multimedia streaming
through the network was applied with the help of the Differential Pulse Code Modulation (DPCM)
compression algorithms that enables compressing the speech data to half of its original size. The
modules. The home automation system is intended to control all lights and electrical appliances in
a home or office using voice. The system has been tested and verified, with voice recognition in
conjunction with ZigBee network we can end the complication of writing in case of wired
(Ashristha, 2019) made a system in which devices are controlled either by giving voice commands
through a user friendly interface. Node MCU and raspberry pi are two boards being used. The
devices connected to the Node MCU can be controlled by giving voice commands with the
assistance of an android app and internet connection. The functionalities are made possible by the
android application named IFTTT. The devices that are connected to the raspberry pi can be
controlled through a user friendly interface. This technique is more developed than other home
(Rahul Biwash) looked into a system designed to be expandable with web-integration possibilities.
This makes it a worthy test bed to examine various algorithms for artificial intelligence-based
Experiments have been examined with different personnel speaking same command results in
good accuracy (100% for quiet background and above 90% for noisy background) of
performance, which proves that the system is as viable as its commercial counterparts.
(Sourav DE, January 2004) looked into the extraction of voice features being done by MFCC
(Mel-frequency cestrum coefficients) algorithm. The training process fully dependent on MFCC,
but afterwards three different models had to be utilized for testing purpose. HMM, DWT and VQ
have been used for comparing and the best result obtained in each case observed and put down.
Accuracy level arrived in this format is almost above 80% in both genders. The efficiency of this
recognition could be developed to over 90%. This can be utilized for the purpose of biometric tests
like retina and finger print scan. This process can be adopted to grant access in various zones like
(Li Xinyu, 2013) made a system consisting of cell phone apps, a server and smart elements.
Connection between all these parts is dubbed as the real internet which basically means that you
can actually use the whole system anywhere. What makes Google voice better is the voice
recognition which is pretty seamless and accurate. Improvements could be made by using some
simple machine learning and statistical methods to derive the user’s habits by checking the activity
records in the database, making improvements on the algorithm to make the system much smarter
and faster.
(Prof K.K Mathew, April 2016) procured a phase of the project in the area of voice controlled
home with the aid of GSM as an added feature and also where distance is no constraint, therefore
the appliances can be controlled from a wide range/distance. Along with the appliances, a regular
check can be maintained not only on the doors and windows but also on the LPG levels and water
levels.
(Jinsoohan, 2009) proposed an automatic standby power cut-off outlet as a ZigBee end device for
the energy-saving room architecture. A ZigBee controller with IR code learning functionality was
in charge for communicating with the power outlets and reducing intensity of the light. There are
also button switches on the controller manually operating the respective outlets and the reduction
of the light. After the ZigBee controller learned the IR codes from a conventional IR controller, the
user can then press the button on the IR controller to wake up the respective appliance.
(Hung, 2008) designed the remote power switching with current measurement outlets for the
power managed system. They used visual basic as the interface software for the framework so the
graphic user interface can provide an approachable operation of a typical home outlet. The
functions of the PC control software include the buttons, the reports of control statuses, and the
(D. giusto, 2010), (VladmirVujoc, 2015) and (Buhur, 2005) all saw the project matter using an
IOT model to envision billions of sensors connected to the internet through wires and other
communication technologies. The sensors would generate large amounts of data which needs to be
analyzed, interpreted and utilized for monitoring and controlling the electrical and electronic
appliances at home remotely by simply using a Smartphone, implementing a low cost, flexible
home automation system. It also improves the use of wireless communication which provides the
(S.M.AnamulHaque, 2006) proposed two ways to control home appliances, which are by utilizing
timer and by utilizing voice commands. The software framework is developed on Virtual Basics
6.0 on a personal computer, and devices are controlled using personal computer parallel port.
(A.K Gnanasekar, 2012) proposed a voice recognition-based automation system for the sole
purpose of the industry (place of application) which utilizes HM2007 voice recognition module for
the voice recognition function which provides a maintenance engineer and a disabled person in the
utilizing the internet. The proposed work is condoned in networking our mobile of various
appliances via a smart logic circuit. It entails smart logic circuit linked to the appliances. Status of
all home appliances can be controlled by users from remote areas with the help of the users’
mobile phone. The various system functions supported are temperature and humidity, gas leakage
detection, control appliances etc. The designed system in addition to monitoring the sensor data,
like temperature, gas, light, motion sensors, also put to work a process according to the
requirement, for example, switching ON the light when it gets dark. It can also store the sensor
(Jain Aayush) and (Sohibat TALLAT, December 2014) both have the same view describing the
workings behind implementing a voice recognition algorithm in MATLAB. The algorithm uses the
discrete Fourier transform in order to compare the frequency spectra of two voices. There are two
stages of systems starting with Registration and then Testing. In the first stage, silence is needed
for the voice print to improve the precision of the recognition. The feature MFCC is extracted for
recognition. In testing session voice, print of an unknown speaker is taken then silence is required
and so the likelihood of finding a corresponding person in the database is relatively feasible.
security focused system which unlocks only when a recognized person speaks a voice password
otherwise the system will not unlock. However, taking the voice recognition in another dimension,
going further by utilizing a tiny microcontroller with real-time speech processing, which basically
means storing samples in a memory location wouldn’t be needed, rather implementing band pass
filter in programming language using fixed-point format on the microcontroller. Analysis of voices
can be done with correlation and regression method to compare the voiceprint of different words;
these methods may vary in strength to recognize the same word. This system is quite seamless and
interesting.
(Mukesh Kumar, October 2015) procured that voice recognition based home automation system
was built and put to use a system specially orchestrated for the people suffering with paralysis and
for the elderly. The adjustable bed offers three rises; sleep position, rest position and sitting
position and according to the user comfort position by voice commands. The use of voice
commands eradicates the need of remote controllers and other electronic device and makes it easy
to relate with the system to perform automation and control electrical devices. The component
buzzer allows persons with special needs to notify the guardians whenever the person needs help.
The illumination sensor automatically turns off the lights when the sun light is enough to see
things around and a time delay is added so that if the user forgot to turn off lights or any device,
(Hashimah, 2004) looked into the project matter applying voice biometric for security purposes, in
which the project voice is the key for accessing the door being secured. This system is produced to
exploit the intense security feature of voice used to unlock a door after a series of password is
entered through the keypad installed along with the system. By having this way of control, the
security of the area is prompted as a voice is unique each person. This project is schedule before
(Mathpati, 2021) procured the complete setup of this proposed system which is measured using a
microphone that is associated with a raspberry-pi.This raspberry-pi has a software interface called
(ALEXA) which transmits the voice commands in the form of discrete binary to the
microcontroller. The base station entity profits off of the decision according to the voice
instruction and directs the instructions to the remote station though the internet. The remote
method takes the command over Wi-Fi enabled internet server and performs the command
function.
All reviews above are similar to this project which is voice activation control but with a analyzed
from a different perspective and applied in a different manner. All projects including mine has
been specifically designed to meet the immediate needs of consumers, from the areas of security to
people with special needs and generally to satisfy the comfort of living.
Taking the reviews and extensive research done into further consideration, this project is unique
due to the range of wireless communication it offers between the voice recognition system and the
home automation system of up to 100 meters distance, as well as the compatibility, portability of
The system has two parts, namely; hardware and software. The hardware system consists of
Arduino UNO board, Bluetooth Module HC-05, Infinix Note 8i Android Phone and Home
Appliances such as Electric bulbs, standing fan, television set, refrigerators etc. The software
system consists of two softwares, The Bluetooth terminal application and the Arduino Integrated
Development Environment (IDE). Arduino IDE software is used for this entire programming
This system is controlled by an Android application which establishes the connection with
Bluetooth module HC-05 and commands are sent via Bluetooth to Arduino. It may be controlled
A variety of techniques can be utilized, depending on the goals of the project, to finish any project.
So, there are specific approaches that can be taken into account when designing software and
hardware. The following techniques are some of the most popular ones when it comes to software
development.
• Waterfall Model
• V-shaped Model
• Evolutionary Prototyping
• Spiral Model
• Agile Development
So, in contrast to other techniques, I picked the waterfall way of system development
linear approach. In a waterfall workflow, each stage of the process must be finished before
going on to the next. While there are many different project management approaches,
waterfall is best suited for initiatives where the objectives are clearly outlined from the
• Keeps the time schedule for each phase from its starting point to the endpoint
• Every step at system development lifecycle (SDLC) has a unique deliverable. Another
important aspect is its sequential model, where the progress is seen in the slow and
downwards flow (like the water is failing from spring) all through to the end of the
software development to follow, which involves not only software development but also,
It is an important technique in terms of getting all the statistics which were applied before or while
performing a project. As this is a product-based project, a deep qualitative and quantitative analysis
is not required, although a thorough understanding of the different procedures are required. As we
have discussed various different controlling mechanism via android-based home automation which
shows the number of procedures that are used for managing home appliances.
According to a study by (go-assist.co.uk) they have taken a survey of the adult aged between 2565
years old asking them about the smart home, whether they like it or not. More than 700 people
among thousand said they would love to have a smart home. People would like to have their home
automated considering security, monitoring, cost and energy, convenience, and protection. There is
also a data for security of a home automation done by (Greenthechmedia.com) we also has
collected data from the literature review. The literature reviewed has not only given us the reason
to pursue this idea in a better way, but it has also helped us to identify the reason for utilizing this
android-based technology. Previous trials and experiments are the major sources for adopting
better solutions for future trials, and it has totally helped us to a certain level. Good understanding
of the literature has helped us gain our objectives efficiently, and, it has helped us consider the
To accomplish the project, we had to go through various software methodologies, so that we could
use the one which is best to fulfill the requirements in an efficient manner. There are many
software tools available, in our case, after careful analysis, we have chosen
3.3.1. AMR VOICE INTERFACE, because of its simplicity and efficiency. There is other software
that we could use, but we decided to use AMR VOICE INTERFACE as this is easy to make an
android application. There are android studio and eclipse that use java language to make
applications, but our target is to achieve the project in a much simpler and efficient manner, other
android studies are quite complicated and some are less efficient. Because of this, we have decided
to go for the APP INVENTOR instead. The research is realized with the help of an Android based
application known as the “AMR Voice” which can be downloaded from an open-source website
using Google search. The application uses Google voice recognition system for speech recognition.
APP DEVELOPMENT: When we connect our Smartphone with HC-05 Bluetooth module through
the above app we would automatically get connected to the app and we will be able to see number
of buttons named as ON and OFF of. To connect the app with a Bluetooth device we utilize the
button at the bottom and to exit the app we click on the exit button. Hence, home appliances can be
automatically controlled through this Arduino Bluetooth Control device. In addition, we will be
When programming the microcontroller from pc, a cable for serial, parallel, or USB
communication and an Arduino Uno board is used with Arduino IDE software. The Arduino IDE
software is a specialized program in the Windows environment for writing programs for the
The designed Home Automation system contains three main hardware components, the Arduino
UNO board, 4- Channel 5V relay Module and HC-05 Bluetooth module. A Smartphone is used to
provide communication between Arduino UNO board and Bluetooth module using a Smartphone
application named as Arduino Bluetooth Control Device (AMR). In this project, Bluetooth module
HC05 and Arduino Uno board are used for hardware implementation. The Bluetooth module
2.45GHz. Arduino Uno microcontroller interprets user instructions and Relay module manages the
device switching, Bluetooth used wireless technology for data transfer, establishes the connection
between the microprocessor and the Smartphone for automation of home appliances (bulb, socket
and others).
computer, used to write and upload computer code to the physical board. The Arduino uno is a
microcontroller board on the AT mega 328p. it has 14 Digital input/output pins (of which 6 can
used as PWM outputs), 6 analogs Inputs, a 16 MHz crystal oscillator, a USB connection, a power
jack, an ICPS Header, and a reset button. it contains everything needed to support the
microcontroller. Simply connect it to a computer with a USB cable or power it with an Ac to Dc
Operating Voltage 5v
SRAM 2KB
EEPROM 1KB
• VIN: The input voltage to the Adriano board when it's using an external power source (as
opposed to 5 volts from the USB connection or other regulated power source). You can
supply voltage through this pin, or, if supplying voltage via the power jack, access it
• 5V: This pin 5V from the regulator on the board. The board can be supplied with power
either from the DC power jack (7 - 12V outputs a regulated), the USB connector (5V), or
• 3V3: A 3.3-volt supply generated by the on-board regulator. Maximum current draw is
50 mAh.
• Memory: The ATmega328 has 32 KB (with 0.5 KB used for the boot loader). It also has 2
KB of SRAM and 1 KB of EEPROM (which can be read and written with the EEPROM
library).
• Input and Output: Each of the 14 digital pins on the Uno can be used as an input or output,
using pin Mode (), digital Write (), and digital Read () functions. They operate at 5 volts.
Each pin can provide or receive a maximum of 40 mAh and has an internal pull-up resistor
functions.
• Reset: Bring this line LOW to reset the microcontroller. Typically used to add a reset
A relay is defined as an electromechanical switch. Historically, the first relay was used in long
distance telegraph circuits as amplifiers, and they were also used in early computers to perform
logical operations. There are various kinds of relays operating at different voltages. A trigger
voltage is always considered when circuits are designed. When a circuit is built, the voltage that
will trigger it has to be considered. In this paper, the relay circuit is used to turn the appliances
ON/OFF. The high and low voltage signals received by the relay are supplied by the Arduino Uno
microcontroller.
The means of wireless data exchanging over a short distance is termed Bluetooth technology. It
uses short wavelength UHF radio frequency from 2.4 to 2.485 GHz range. It’s applicable to mobile
devices and personal area networks (PANs). The Bluetooth module being used allows us to
transmit and receive signals. In this design, the transmitted text received by serial port of the
Arduino microcontroller is sent by the Bluetooth through the android smart phone. There are so
many Bluetooth modules available in the market, but HC-05 Bluetooth module is used in this
design. It is s serial port protocol module that is user friendly with a coverage range of 9m
depending on the level of environmental interference. Serial port Bluetooth module is fully
qualified Bluetooth V2.0+EDR (Enhanced Data Rate) 3Mbps Modulation with complete 2.4GHz
radio transceiver and baseband. It connects automatically to the last device on power as default
with a slave default band rate of 9600 and pairing pin code of “1234” as default.
Figu
re 3.4.3 - BLUETOOTH MODULE HC-06
3.4.5 RESISTOR
To enable the efficient operation of Arduino Uno, we have used few resistors, this is to ensure the
safety of some vulnerable hardware which can be burnt due to high voltage, the resistors provide
Figure 3.4.5
certain set of symbols that illustrate the actions taken at each stage and justifies the order in which
each step is carried out one after the other. The data flow diagram that follows shows the entire
The project’s key component is the microcontroller. The diagram shows how voice commands are
obtained from a mobile device’s or computer microphone and then sent on to the Arduino.
Following the Arduino’s execution of the command, the relay board receives the instructions to
turn on or off the home appliances (fan, light) in accordance. When the relay board is turned ON or
The main reason for this circuit diagram is for better understanding about the all connection of the
system. It is a graphical representation of boards and wires all at once. Our project component is
connected to one another, it demonstrates how the Arduino Uno device is connected to the rest of
Additionally, a Bluetooth module is connected, and it is this module’s job to receive signals from
Amrutha, S., Aravind, S., Ansu M., Sugathan, S., Rajasree, R., and Priyalakshmi, S. (2015).
Voice Controlled Smart Home, International Journal of Emerging Technology and Advanced
Akbar satria, M. l. (2015).the frame work of home automation system based on smart home.
Aqeel-ur-Rehman, R. A. (2014). Voice Controlled Home Automation System for the Elderly or
Disabled People. Journal of Applied Environmental, 10.
AwadallaTaifour Ali, E. B. (April 2017). Voice Recognition Based Smart Home Control System.
International Journal of Engineering Inventions, 5.
March 2017
13-14
B.BHavani, T. a. (2013).a sustainable automated system for elderly people using voice
reconition and touch screen technology. Internal journal of science and research, 2.
Barbu, T. (July 2009). Comparing various voice recognition techniques.Conference Paper, 26.
energy sources.
Devarsh and kodgire (2016). Speech Recognition System for Voice Controlled
GayatriR.Shinde, J. N. (July 2015). Voice and Non Voice Control Based Wireless.
Issue- 5, 8.
Mewada, A., Mishra, A., Gupta, M., Dash, R., and Mulla, N. (2016). Voice Controlled Home
Pranav, B., Vedant, R., and Aditya R. (2016), Voice Controlled Home Automation, International
2717-2718.
system for the elderly and the physically challenged. International conference on
Rosslin R.J. and Kim, T,-H. (2010), Applications, Systems and Methods in Smart Home
15(3), PP 37-47.
CHAPTER 4
This chapter provides a detailed breakdown, the results of the voice activation control system
which was tested using different methods. The discussion attempts to highlight the results, the
benefits, pros and cons of the results obtained in this project and the general flexibility of the
system.
4.0 Results
Three persons with completely different intonations and of different age groups were used to test
the reliability of the voice (speech) recognition application and its effectiveness so as to test the
systems switching mechanism. Each person said the controlling command about six times (ON
thrice and OFF thrice) to test the response accuracy of the system. A table was compiled to show a
data sheet of the results retrieved from the voice (Speech) test.
Commands Number of persons Used for the voice test (Out of 6 total commands
each)
Person(s) A B C
The table above provides a well detailed data overview of the commands spoken by the three
different people that were picked to test the feasibility of the voice (speech) recognition of the
system. Each command corresponds with the various lighting points and electrical device that can
be turned ON or OFF using voice (speech) command. To give a command to each individual
lighting point, including the electrical fan, a preprogrammed AI virtual assistant called “Avatar” is
summoned then the ‘ON’ and ‘OFF’ speech command is spoken immediately after. This can be
seen from the way each item (speech commands) has been very well detailed under the command
section of the data table. The other columns, A, B and C represents each individual person used to
carry out the speech command tests and below each individual column is the total number of times
each person spoke the ON/OFF command into the corresponding system., supported by means of
the AMR software interface integrated on the Android phone. The “Turn ON’ all appliances voice
command switches on all appliances connected to the relay whereas the ‘Turn OFF’ voice
command all appliances switches off all electrical Points.
ON OFF Total
Bedroom 5 7 12
Living Room 7 8 13
Kitchen 9 7 16
Electric Fan 9 9 18
All 8 7 14
Table 4.2 above shows a vivid breakdown of the results obtained from table 4.1. In this table, two
different columns for the ON and OFF sequences have been formulated with a detailed breakdown
on the total number of successful responses per command sequence.
While testing the system, all electrical points were successfully turned ON/OFF using the AMR
voice (speech) interface supported by the ATmega 328p microcontroller. Below are visual results
obtained from the practical working principle.
4.1 Discussion
The system prototype was successfully designed, constructed and implemented. From table 4.1 and
4.2, the results obtained provide an accurate data of the number of times the voice (speech)
command was successfully implemented. For this test, a number of three different people of
different age groups and tribal backgrounds were selected to test the seamless flexibility between
the AMR software interface and the programmed Arduino Microcontroller (ATmega 328p) to see
how the system performs and responds to these commands. The initial distance recorded between
the microphone on the android phone and the system was about 2 meters. After a series of
successful and failed responses, additional distances (5meters, 10meters, 20meters and 25meters)
were covered to test the range compatibility between the android phone and the Bluetooth module
in the system. When the voice commands were issued, it was discovered that the users had to
speak quite audibly and faster for the system to respond accurately. After this bypassing this
temporary limitation, the success rate of the system was concluded at an efficiency of 95%.
During the process of system testing, the arduino microcontroller (AT mega 328p) seemed to take
a while (10 seconds) before processing each commands transmission sent from the AMR software
Engine. In addition to this, it was also discovered that a user’s voice command could not be
recognized due to certain conditions such as;
Background Noise
Speech deficiency
Intonation
Therefore, under these conditions the success rate of the AMR software interface was calculated at
an efficiency rate of 82%. Nevertheless, the system reached all expectations by demonstrating a
relevant flexibility in adapting to different scenarios and ascents while properly responding to user
requests. During the process of building this system prototype, several benefits as well as
challenges were discovered;
4.1.1 Benefits
From the results curate above, it is quite evident the flexibility of the system in terms of controlling
home appliances just by the use of the human voice. The user is relieved of the stress of operating
conventional switches and remote control with just the use of their voice from any corner of the
home. Also the user need not worry about the immense knowledge of the English language, rather
just by saying the electrical point name and the corresponding command assigned to that particular
point and telling it to turn ON or OFF will enable the user have full control of the system. Though
this system was designed to generally reduce human effort and improve comfort, it would be of
much more importance to the elderly and people with disabilities. It would enable them control
much of the home without having to move about the place or stress themselves too much.
The AMR Android application installed has a great user interface and impeccable user experience
which helps the user to understand its functionalities and in a small amount of time. This system
has been designed with cost effective materials which makes its scalability quite easier as the
device can be incorporated into any building or homes of any structure and design using electrical
appliances.
4.1.2 Challenges
In as much as the immense access rate recorded during the implementation of this project, some
challenges were faced as well. For the AMR voice command, when making a speech command,
series of wrong voice sequences were outputted due to background noise conditions, inaudible
speech commands etc. also the issue of delay between the arduino microcontroller and the voice
command.
CHAPTER 5
Considering the inevitable and ambiguous changes around the globe, while the human population
keeps getting older coupled with other natural disparities, advancements in technology continues to
grow rapidly in different sectors. But, in this project a common sector has been highlighted, which
is the home automation system based on android voice recognition. This system is targeted
specifically at the elderly and physically impaired people while catering towards the needs of the
general public as well. The prototype developed has been designed in such a way that it can
control electrical devices in a home such as the electric bulbs, switches, electric fan, door locks etc.
The system implements an automatic speech recognition engine known as the Adaptive Multi Rate
(AMR) speech through series of programming codes and training voice commands. The system
also implements the wireless network using a wireless Bluetooth module for efficiency, low power
consumption and long distance range (50 meters). The mode of implementation utilized in this
project was technically selected to make the system as user-friendly as possible and therefore the
preliminary test results are promising. During the course of this project some factors were
procured;
5.1 PROS
This proposed system is able to provide many advantages, some of which include;
Safety
Security
Improved Comfort
Cost Savings.
5.2 LIMITATIONS
During the course of developing this prototype, there were not many problems encountered but,
given that this system isn’t ideal some issues were bound to occur some of which are;
The voice recognition system recognizes error in response to background noise, and
requires absolute silence to work properly else it could pick noise signals and produce error
in response.
The receiver and transmitter circuits will work only at a voltage range of 3.37v-9v, so
batteries and voltage regulators used were of good quality and carefully kept under check.
easy and efficient to incorporate almost everything in our daily work activities into this system to
make it work seamlessly and make them smarter, so as to enable the system carry out tasks on its
own. In line with this very project some other possible advancements of this system arfe;
i. To enable the control of homes with solar power and other renewable systems via Android
application.
ii. To enable the control of other home appliances like the coffee machine, washing machine
etc.
iv. Incorporating other home security systems to this system to make the home safer.
5.4 RECOMMENDATIONS
i. For the system to be effective to different ethnicities on the African continent there needs to
be clear sets of libraries in the Android application to allow the incorporation of the Igbo
language and other native languages in the country and on the continent.
ii. Introduction of a user identification function to the voice recognition software as a type of
Amrutha, S., Aravind, S., Ansu M., Sugathan, S., Rajasree, R., and Priyalakshmi, S. (2015).
Voice Controlled Smart Home, International Journal of Emerging Technology and Advanced
Akbar satria, M. l. (2015).the frame work of home automation system based on smart home.
Aqeel-ur-Rehman, R. A. (2014). Voice Controlled Home Automation System for the Elderly or
Disabled People. Journal of Applied Environmental, 10.
13-14
B.BHavani, T. a. (2013).a sustainable automated system for elderly people using voice
reconition and touch screen technology. Internal journal of science and research, 2.
Barbu, T. (July 2009). Comparing various voice recognition techniques. Conference Paper, 26.
energy sources.
Devarsh and kodgire (2016). Speech Recognition System for Voice Controlled
Name Description
Jumper Wires
Total
Appendix B - Code