ISSN: 2319-5967

ISO 9001:2008 Certified

International Journal of Engineering Science and Innovative Technology (IJESIT)
Volume 4, Issue 1, January 2015

Speech Recognition Based Wireless

Automation of Home Loads- E Home
 Amrutha S, Aravind S, Ansu Mathew, Swathy Sugathan, Rajasree R, and Priyalakshmi S
Department of Electronics and Communication Engineering,
Sree Buddha College of Engineering for Women, Kerala, India

Abstract— Each day we are aiming for a relaxing and more laid back home. Technology plays a major role in making
our homes more automated and hence laid back. This research aims to design and implement a cost effective but yet
flexible, adaptable, and secure Home automation system. Paper presents design and prototype implementation of a basic
home automation system based on SMS technology and voice recognition. When automating a home load not available in
the visible range, fault identification system in this design helps the user to ensure that their home appliances had gone
exactly ON or OFF. Each home load will be having two commands ON and OFF commands. Automation of 2 loads such
as fan and light has been tested by giving 4 voice commands through personal computer. When user creates his own profile
and automates the load speech recognition accuracy of more than 90% is achieved. Other people who were allowed to
automate the load by the user can use user profile and achieve a speech recognition accuracy of 75% in the same personal
computer.
Index Terms— SMS technology.

I. INTRODUCTION
The world has become a global village due to revolution in the technology; in this revolution the IT (Information
Technology) played an important role. Similarly the revolution in IT makes mankind dream come true to have an
automated home. Home automation use microprocessor-based intelligence to integrate or control electronic
products and systems in the home. The incentive behind home automation is efficient utilization of electricity. So a
variety of research and many solutions had proposed on home automation. These systems use PC, mobile internet,
GSM Bluetooth and ZigBee network etc. Generally, home automation research targeted many needs; some
applications fulfill the sophisticated and luxury requirements; other focuses the special needs like elderly and the
disabled etc. In such applications voice recognition technology is used Wireless communication based home
automation system has gained a high momentum for the last couple of years. Wireless communication reduces the
complexity related to the installation and maintenance compared to its wired counterpart. A typical wireless home
automation system comprises battery operated and low power wireless sensors and actuators. Bluetooth, Wi-Fi,
and ZigBee are the popular choice for the backbone of such systems. Wireless network based smart home systems
have become very popular as they provide comfort, security, and safety. Moreover, they support remote monitoring
facilities. The availability of cheap wireless sensors, actuators, and modules has reduced the gap between the
luxury and mass market segmentations of home automation technologies. However, wireless home automation
system has some limitations too.

The home automation needs to make use of latest technological advancements. This project aims to design and
develop a home automation system which is wireless and can be controlled in multiple ways to give more
accessibility and control over the system. The purpose is to develop and design an automation system which is
accessible remotely at the same time locally in a user friendly way. Yet cost effective, robust, portable and easily
operable so that it could be widely accepted for multiple needs. Wireless communication in home automation is
centered on low-power RF Zigbee wireless communication modules. Voice commands and GSM messaging are to
be used to control the automation of household electrical appliances.

II. RELATED WORK

Home automation is the automatic or semi-automatic control and monitoring of household appliances and
residential house features like doors, gate and even the windows. This is a demonstration of how to design and
build a multi-purpose wireless system that can switch OFF and ON any electrical household appliance depending

179
 ISSN: 2319-5967
ISO 9001:2008 Certified
International Journal of Engineering Science and Innovative Technology (IJESIT)
Volume 4, Issue 1, January 2015
on the voice produced by the user. Thoraya Obaid et al. [1] proposed a voice controlled wireless smart home
system for elderly and disabled people. The proposed system has two main components namely voice recognition
system, and wireless system. Lab View software has been used to implement the voice recognition system. On the
other hand, ZigBee wireless modules have been used to implement the wireless system. Based on the received data
at the wireless receiver associated with the appliances desired switching operations are performed. The proposed
system is a low cost and low power system because ZigBee is used. Additionally the proposed system needs to be
trained of voice command only once.

Another home automation system was proposed by Dhawan S. Thakurand and Aditi Sharma [2]. That demonstrates
a system that can be integrated as a single portable unit and allows one to wirelessly control lights, fans, air
conditioners, television sets, security cameras, electronic doors, computer systems, audio/visual equipment‟s etc.
and turn on or off any appliance that is plugged into a wall outlet, get the status of different sensors and take
decision accordingly. The overall system is controlled from a microphone which is connected with HM 2007
speech recognition chip. This chip sends the voice commands in binary sequence to microcontroller. The base
station unit takes decision and sends the commands to remote station by ZigBee transceiver.

Khiyal et al. [6] proposed a system for controlling home appliances remotely that is useful for the people who are
not at home mostly. The main objective of the system is to provide security and control the home appliances such
as AC, lights and alarms. The system is implemented by SMS technology that is used to transfer data from sender
to receiver over GSM network. Also Haque et al. [7] proposed a system that controls the home appliances using the
personal computer. This system is developed by using the Visual Basic 6.0 as programming language and
Microsoft voice engine tools for speech recognition purpose. Appliances can be either controlled by timer or by
voice command.

III. PROPOSSED METHOD

a) SYSTEM MODEL
The system model is shown in Figure 1. The system consists of the following basic components (i) automatic
speech recognition system, (ii) control units, (iii) wireless system and (iv) application and home appliances.
Automatic speech recognition (ASR) system can be defined as an independent and computer‐driven transcription
of spoken language that allows a computer to identify the spoken words captured from a microphone or telephone
and converts it into written texts. The main components of an ASR are (i) a microphone, (ii) speech recognition
software and (iii) a computer. Through a speech recognition program/application, the computer is able to process
words one says and turn them into text that is displayed on the screen. There have been many research activities on
the speech recognition system. The fundamental reasons of these research activities are (i) accessibility for the deaf
and hard of hearing, (ii) cost reduction through automation, and (iii) searchable text capability.

The control unit (CU) coordinates the components of a computer system. It fetches the code of all of the
instructions in a program. It directs the operation of the other units by providing timing and control signals. There
are different types of control program available including MATLAB, C++, and Lab View. In this work we choose
MATLAB because of the following reasons: (a) it is easier to build a large program piecewise using small amounts
of code, (b) it is easy to control the interfaces between hardware, (c) it is easy to find compatible hardware in the
market, (d) it is simple to integrate with other hardware and software, and (d) it is easy to create the user-interface.

Speech Control Wireless Control Application

recognition unit for system unit for and home
MATLAB embedded appliances
section section

Fig 1: System model

180
 ISSN: 2319-5967
ISO 9001:2008 Certified
International Journal of Engineering Science and Innovative Technology (IJESIT)
Volume 4, Issue 1, January 2015
Wireless networks and sensors are playing important roles in emerging pervasive computing technologies that are
required for the realization of smart homes. Effectively all wireless technologies that can support some form of
remote data transfer, sensing, and control are candidates for inclusion in the smart home portfolio. In this work we
used ZigBee wireless system. The control unit for the embedded section is any microcontroller. It co-ordinates all
the functions that performed by the control part.

b) System Design
The proposed method is to use a PC along with MATLAB software for speech processing and recognition. The
output of the PC will be sent, through the ZigBee transceivers, to the control part, where a microcontroller will
select the required device according to the input voice command.
The system can be divided into 3 main parts:
1. Audio processing part microphone and PC with MATLAB software
2. Transmission part ZigBee transceivers
3. Control part microcontroller, relays and GSM module

Audio processing part

Microphone PC Zigbee

Transmission part

Zigbee

Device 1 Relay GSM

Micro-
Controller

Device 2 Relay LCD 16x2

alphanumeric

Control part

Fig 2: Block Diagram

Audio processing part
The voice commands will first be captured and processed in MATLAB according to the voice recognition method
used. The captured the speech is compared with the previously trained words in the database and recognizes the
speech using appropriate algorithm. After successful identification of the commands, control characters will be
wirelessly sent through the ZigBee transceivers to the control part. The proposed system was implemented using

181
 ISSN: 2319-5967
ISO 9001:2008 Certified
International Journal of Engineering Science and Innovative Technology (IJESIT)
Volume 4, Issue 1, January 2015
two home loads such as light and fan. So, the database contains five words, they are fan on, fan off, light on, light
off and noise. The control characters that send to control part are „*a‟, „*b‟, „*c‟, „*d‟ for fan on, fan off, light on,
light off respectively. These control characters are given to the transmission part to control the home appliances.

Transmission part
The ZigBee transceivers constitute the transmission part. ZigBee transmitter is connected to the audio processing
part and ZigBee receiver is connected to the serial communication port of control part. There are two different
ZigBee kits one is USB compatible kit with PC and other one is RS232 protocol compatible. Using these ZigBee
transceivers the control characters reaches the control part.

Control part
The control unit for the embedded section is any microcontroller. In this we use an ARM based LPC2148
microcontroller. Applications and home appliances are the last step of the proposed system. Each device connected
with the network must have a switching circuit to turn it ON/OFF. The status of each device is monitored by using
toggle circuit. The control part will on/off the device according to the control characters.
c) System Implementation
The proposed method is aimed at designing a voice controlled and GSM based smart home system. The system is
designed in such a way that it is easy to install and use. The system has two main sections; they are MATLAB
section and embedded section. MATLAB section uses a PC with MATLAB software for speech processing and
recognition. The speech recognition is done with the help of MATLAB coding. After recognition, corresponding
control characters are sent through the ZigBee transceivers to the control part. Microcontroller in the control part
will select the required device according to the input voice command. The devices can also be controlled from
distant locations through SMS. So, a GSM module is associated with the control part.

Table 1. Voice commands and corresponding control characters

Voice commands Control characters

Fan on *a

Fan Off *b

Light on *c

Light off *d

Fig 3. System implementation

182
 ISSN: 2319-5967
ISO 9001:2008 Certified
International Journal of Engineering Science and Innovative Technology (IJESIT)
Volume 4, Issue 1, January 2015
IV. RESULTS AND CONCLUSION
Here we implemented speech recognition based home automation system which can be controlled by voice as well
as through SMS technology. Voice recognition based Wireless Home Automation Based on ZigBee is a very useful
for the adults and physically disabled persons, who are not able to do various activities efficiently when they are at
home and need one‟s assistant to perform those tasks. With the Voice Recognition along with ZigBee network we
can eliminate the complication of wiring in case of wired automation and also it prevent to get up and down again
and again to on/off appliances. ZigBee Home Automation provides operating range much higher as compared to
Bluetooth and other wireless sensor module. On the other hand with voice recognition system, it provides secure
access to home. So when we are living in a fast world where everything is changing with in no time such security is
essential.

REFERENCES
[1] Thoraya Obaid, “Zigbee Based Voice Controlled Wireless Smart Home System,” International Journal of Wireless &
Mobile Networks (IJWMN), Vol. 6, No. 1, February 2014.
[2] Dhawan S. Thakur and Aditi Sharma, “Voice Recognition Wireless Home Automation System Based On Zigbee,” IOSR
Journal of Electronics and Communication Engineering (IOSR-JECE), Volume 6, Issue 1 (May. - Jun. 2013), PP 65-75.
[3] Parameshachari B D et al, “Study on Smart Home Control System through Speech,” International Journal of Computer
Applications., Volume 69– No.19, May 2013.
[4] Kailash Pati Dutta, Pankaj Rai and Vineet Shekher, “Microcontroller based voice activated wireless automation system,”
VSRD-IJEECE, Vol2 (8), 2012, 642-649.
[5] A.J. Bernheim Brush, Bongshin Lee, Ratul Mahajan, Sharad Agrawal, Stefan Saroiu, Collin Dixon(2011), “Home
Automation in the Wild: Challenges and Opportunities,” Proceedings of ACM CHI Conference on Human Factors of
Computing System, May 7-12, Vancouver, BC, Canada.
[6] Malik Sikandar, Hayat Khiyal, Aihab Khan, and Erum Shehzadi, “SMS Based Wireless Home Appliance Control System
(HACS) for Automating Appliances and Security,” Information Science and Information Technology, Vol 6, Pp.
887-894, 2009.
[7] S. M. Anamul Haque, S. M. Kamruzzaman and Md. Ashraful Islam, “A System for Smart-Home Control of Appliances
Based on Timer and Speech Interaction,” Proceedings of 4th International Conference on Electrical Engineering, pp.
128-131, January, 2006.

AUTHOR BIOGRAPHY
Amrutha S, pursuing final year B.Tech degree in Electronics and Communication Engineering from Mahatma Gandhi
University, Kerala, India.

Aravind S, Assistant professor in the Department of Electronics and Communication Engineering, Sree Buddha
College of Engineering for Women, Mahatma Gandhi University, Kerala, India. He obtained M.Tech degree in
VLSI and Embedded Systems with Distiction from Govt. College of Engineering Chengannur, Cochin University
in 2012. He received his B.Tech Degree in Electronics and Communication Engineering with Distiction from
the main campus of Cochin University of Science and Technology, School of Engineering, Kerala, India, in 2009.
He has published nine research papers in various International Journals.He has presented three papers in National
Conferences. He has excellent and consistent academic records,very good verbal and written communication skills.
He has guided nine projects for graduate engineering students and one project for P.G student .He has academic experince of 3 years and
industrial experience of 1.6 years. For Post Graduate students he has handled subjects such as Electronic Design Automation Tools, VLSI
Circuit Design and Technology ,Designing with Microcontrollers and Adaptive Signal Processing. He taught subjects such as Network
Theory, DSP, Embedded Systems, Digital Electronics, Microcontroller and applications, Computer Organisation and Architecture ,
Microprocessor and applications, Microwave Engineering ,Computer Networks and VLSI for B.Tech students.

183
 ISSN: 2319-5967
ISO 9001:2008 Certified
International Journal of Engineering Science and Innovative Technology (IJESIT)
Volume 4, Issue 1, January 2015
Ansu Mathew, pursuing final year B.Tech degree in Electronics and Communication Engineering from Mahatma
Gandhi University, Kerala, India.

Swathy Sugathan, pursuing final year B.Tech degree in Electronics and Communication Engineering from Mahatma
Gandhi University, Kerala, India.

Rajasree R, pursuing final year B.Tech degree in Electronics and Communication Engineering from Mahatma Gandhi
University, Kerala, India.

Priyalekshmi S, Assistant professor in the Department of Electronics and Communication Engineering, Sree Buddha
College of Engineering for Women,Mahatma Gandhi University, Kerala, India. She obtained M.Tech degree in Applied
Electronics from Anna university, in 2011. She received her B.Tech Degree in Electronics and Communication
Engineering from Kerala University Trivandrum, in 2009. She has guided several projects for graduate engineering
students.She has academic experince of 4 years.She is interested in DCT, Signal Processing and Control Systems.

184