Voice Recognition Based Home Automation System for
Bhujbal, Abhishek Hire, Akash Jadhav, Siddhesh Lendhe.
guidance of Prof. Z V Thorat.
Abstract— The voice recognition based home automation
system was built and implemented. The system is specially designed for the
people suffering from paralysis and also for the elderly people.The use of
voice commands eliminates the need to remote controllers and other electronic
device and makes it easy to interact with the system to perform automation and
control electrical devices. Buzzer allows disabled person to notify the
guardians whenever the person need help. The illumination sensor automatically
turns off the lights when sun light is enough to see things around also a time
delay is added that if user forgot to turn off lights or any device the will be
automatically turned off to conserve energy.
Home Automation System, Physically
Challenged People, Voice Recognition Module V3, Arduino Uno, Adjustable Bed Motorized
any third person’s assistance. The voice recognition based
The home automation systems are gaining
popularity day by day due to their ease of use and wide operations
capabilities. Integrating voice recognition technology to home automation
systems make the system more user friendly and easy to operate. Some require
home automation system to satisfy their needs and comfort while for physically
challenged people it can provide great assistance.
Intelligent home navigation system for
disabled and elderly person proposed a system which uses voice recognition
module for the speech recognition process, an Arduino controller, a wheel chair
and a navigation module.
The Arduino receives the command from the
voice recognition module and move the wheel chair accordingly thus eliminating
the need of system uses Lab view to perform speech recognition and Bluetooth
module with a controller is used to control the devices wirelessly.
While the needs of many individuals with disabilities
can be satisfied with power wheelchairs and voice control home automation, some
members of the disabled
people’s find it is difficult or impossible
to operate a standard power wheelchair. This project could be part of an
assistive technology. It is for more independent,
productive and enjoyable living for disabled
I. system overview
The voice recognition based home automation system
is an integrated system to facilitate the elderly and physically challenged
people with an easily operated home automation system that operates fully on
voice commands. The functional block diagram of the proposed system is shown in
speech input from microphone is given to the voice recognition module where the
speech signal is compared with the previously stored trained voice samples.
Upon successful recognition of voice command the Arduino microcontroller
actuates the corresponding electrical device like turning on lights, and
adjusting bed elevation using the relay module. The data from the illumination
sensor is processed in Arduino controller and based on a set point value the
automatic control action is taken to switch off the lights to save energy. The
buzzer sounds when disabled person need is calling for help or when he needs
II. hardware implimentation
Microphone and Voice Recognition Module
The microphone used to get voice commands to the voice recognition
module is a simple collar type microphone with 3.5 mm jack. Elechouse voice
recognition module v3 is used for the voice recognition process as shown in
Fig.2. The voice recognition module needs to be trained before it can be put to
actually recognize the voice commands. The speech input from the microphone is
given to the voice recognition module and there the input speech is compared
with the previously trained voice commands and if there is a match then control
action through control circuit is taken. The voice recognition module v3 can
store up to 80 commands of 1500ms each in its library and out of 80 only 7
commands can be loaded into recognizer for the recognition process. Thus only 7
commands are effective at a time and to add another 7 commands recognizer needs
to be cleared first. The module has two ways of controlling Serial Port,
General Input Pins. General Output Pins on the board could generate several
kinds of waves while corresponding voice command was recognized. Module has a
recognition accuracy of 99% under ideal conditions.
B. Arduino Uno
The controller used for the proposed system as shown in Fig. 3
is Arduino Uno microcontroller.
The arduino platform provides an inexpensive and easy
way for students and professionals to create devices that interact with their
environment using sensors and actuators. Arduino comes with simple integrated
development environment (IDE) which runs on a PC and allows user to write
programs for Arduino in C or C++ language. The Arduino microcontroller is based
on the ATmega 328. It has 14 digital input/output pins (Out of these 14 pins 6
can be used as PWM outputs) and 6 analog inputs. Ardunio works on 5V D.C and
has clock speed of 16 MHz.
C. Light Sensor
dependent resistor is use to sense the illumination inside the room so that the
system can shutdown the lights when there is sufficient day light to see
anything around to conserve energy.
is main indicators of the designed system through which the guardians of the
disabled people can be alerted to check disabled person when buzzer makes a
sound and take necessary care. If the patient needs any help then by voice
command he or she may turn on the buzzer for help.
E. Relay Circuit
To control the Home appliances relays are used with the
Arduino. .The relays used in the system are 5V-5 pin relay as shown in Fig. 4.
The relay remains in normally closed state. When relay coils are energized the
relay switches from normally closed to normally open state due to
electromagnetic induction .The normally open state (N.O) of relays is used in
the home automation system. Fig. 4 shows the buzzer, illumination sensor and
relay on embedded on the general purpose PCB.
III. SOFTWARE IMPLEMENTATION
The software implementation part of voice recognition based home
automation system implemented using the Arduino controller. It consists of
training of voice recognition module. The voice recognition module needs to be
trained first with the voice commands before it can be put to recognizing
function. The voice recognition module training program is loaded into the Arduino
and then trained with the voice commands. Fig. 10 shows the training process of
voice recognition module using the Arduino IDE. The main code for the home
automation system is written in C++ language in Arduino IDE. Upon successful
recognition of voice command the control action corresponding to that command
This system makes use of Arduino mega. The Bluetooth
receiver is interfaced with arduino in order to accept the commands and then
react accordingly. It operates the loads through a set of relays using a relay
driver IC. Relays are used between loads and the control unit. This system thus
can be used in many domestic applications and in industrial setups.
power supply setup of the system contains a step down transformer of 230/12V,
used to step down the voltage to 12VAC. To convert it to DC, a bridge rectifier
is used. Capacitive filter is used which makes use of 7805 voltage regulator to
regulate it to +5V that will be needed for microcontroller and other components
operation, in order to remove ripples.
The microphone used to get voice commands to the voice recognition module is a
simple collar type microphone with 3.5 mm jack. Elechouse voice recognition
module v3 is used for the voice recognition process. The voice recognition
module needs to be trained before it can be put to actually recognize the voice
commands. The speech input from the microphone is given to the voice
and there the input speech is compared with the previously trained voice
commands and if there is a match then control action through control circuit is
taken. The voice recognition module v3 can store up to 80 commands of 1500ms
each in its library and out of 80 only 7 commands can be loaded into recognizer
for the recognition process. Thus only 7 commands are effective at a time and
to add another 7 commands recognizer needs to be cleared first. The module has
two ways of controlling Serial Port, General Input Pins. General Output Pins on
the board could generate several kinds of waves while corresponding voice
command was recognized. Module has a recognition accuracy of 99% under ideal
handicapped person can use this and become independent.
manpower and dependency on other human drive.
challenged people can use home automation technique to operate home
? Easy to
drive with negligible efforts to move wheelchair and use home appliances.
? compact and economical.
Circuit is complex
Limited range operated
Very complicated to design
VI. Future Scope
For future technology wheelchair would be fully autonomous
that will move automatic based on the user expression and behavior and that
should be fully automatic and wireless.
In this project firstly we are working on the voice based
automatic wheelchair and after that we will combine upcoming latest technology
like software based that will be controlled by computer and GSM mobile phones.
After that we are thinking on putting a biometric feature
in it that should be little bit secured for the user
Instead of using voice we can use eye retina using optical
sensor to move wheelchair accordingly.
Also it can be extended by including GSM that sends an SMS
We are thankful to our
college ‘Bharati Vidyapeeth College Of Engineering” for considering project and
considering us through the various stages of the project report-I. It gives us
immense pleasure to express our sincere gratitude of Prof. Z.V.Thorat for his guidance in selecting this mini
project report and also for providing us with all the details.
are deeply indebted to our respected Head of
Electronics and Telecommunication Department, Prof. P.A. Kharade,
for giving us this valuable opportunity to do this project and we express our
hearty thanks to them for their assistance without which it would have been difficult
in finishing this mini project report successfully.
are also thankful to our respected Principal Dr. M. Z. Shaikh. We convey our
deep sense of gratitude to all teaching and non-teaching staff of Electronics
and Telecommunication Department for their constant encouragement, support and
timely help throughout the mini project report work.
Oberle, S., and Kaelin, A. “Recognition of acoustical
alarm signals for the profoundly
deaf using hidden Markov models,” in IEEE International
symposium on Circuits and Systems (Hong Kong),
Shawki and Z. J., A smart reconfigurable visual system for
the blind, Proceedings of the Tunisian-German Conference on: Smart Systems and
M. Higgins and V.
Pant, Biomimetic VLSI sensor for visual tracking of small moving targets, IEEE
Transactions on Circuits an Systems, vol. 51, pp. 2384–2394, 2004.