Voice Enabled Home Automation using Amazon Echo

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056
Volume: 04 Issue: 08 | Aug -2017 www.irjet.net p-ISSN: 2395-0072
© 2017, IRJET | Impact Factor value: 5.181 | ISO 9001:2008 Certified Journal | Page 682
Voice Enabled Home Automation Using Amazon Echo
Achal S Kaundinya1, Nikhil S P Atreyas1,Smrithi Srinivas1,Vidya Kehav1 ,
Naveen Kumar M R2
1Student,2Assistant Professor, Information Science and Engineering, VVCE, Mysuru
----------------------------------------------------------------------------***-----------------------------------------------------------------------------
Abstract— In recent years, the field of Internet of
Things (IoT) has seen significant investments made by the
research community and the industry. Specifically, the
Smart Home space has been a prime focus with the
introduction of devices such as Amazon Echo, Google
Home, Samsung Smart Things among others. The growth of
an industry results in innovative, economic, and advanced
solutions. In this paper, we focus on making non-smart
homes smart and how to build a robust, cost-effective
system that can be widely used. We power our system
using Amazon Echo, Amazon’s cloud services, its speech
services. A Raspberry Pi 3 is used as the hardware
component for providing smart features for non-smart
homes. We describe the different components of our
product and we show that our system works effectively to
switch on and switch off our appliances.
Keywords— Amazon Echo, Alexa , automation,
non-smart, Internet of Things (IoT) , raspberry pi,
relay;
I. INTRODUCTION
Amazon Echo is a voice-enabled wireless speaker
developed by amazon. The device connects to the voice-
controlled intelligent personal assistant service Alexa,
which responds to the name "Alexa". The device is capable
of voice interaction, music playback, making to-do lists,
setting alarms, streaming podcasts, playing audiobooks,
and providing weather, traffic and other real time
information. It can also control several smart devices using
itself as a home automation hub. Home automation is a
very expensive luxury that a lot of people in India and
other countries cannot afford. The objective of our product
is to provide a cheap and inexpensive way to control non-
smart devices using the power of voice. Amazon Echo is a
smart speaker that has been developed by the Amazon
company that can be used to play music, listen to the news
and control a lot of smart devices. We use the Amazon echo
to develop a skill (app) that will communicate with our
raspberry pi to control our devices.
We use the Publisher-Subscriber design pattern to
communicate between the Amazon Echo and the
Raspberry Pi. The Amazon echo runs a Nodejs program
and the Raspberry pi runs a Python program to
communicate with each other and control the devices.
Whenever we want to turn on or turn off our
appliances, we ask the Amazon Echo to turn the appliance
on or off.
II.RELATED WORK
In this section, we will present the various systems
available in the market and also the recent advancements
in the research working in this area. Most of the state-of-
the-art systems today can be integrated with IFTTT
recipes[1]. To give some context to the reader, IFTTT is the
acronym of If This, Then That. It is an initiative in the
Internet of Things space where several services can be
integrated to provide a robust solution. A. Existing
Products The smart home space has seen a lot of industrial
investment in the recent years. The following are some of
the successful smart home products available today:
Lifx Color 1000: Lifx's second-gen smart bulbs are
brighter and more efficient. It has an easy-to-use app, the
integrations with IFTTT and Alexa, and the fact that Lifx
bulbs don't need a hub is also an advantage.
Philips Hue Wireless Dimming Kit: The Philips Hue
Wireless Dimming Kit is a simple, and affordable way to get
started with smart lighting. It allows you to control the
lights of your home using voice and the internet. It also
allows you to control the intensity of the light.
III.TECHNOLOGY STACK
In this project, we have integrated many technical
components and established a seamless functionality
among them. Our technological stack is delineated as
follows:
• Physical Layer: This layer comprises of the devices
with which the user interaction takes place:
1) Raspberry Pi 3 Model B [11] - enabled with WiFi
2) Amazon Echo - Smart Personal Assistant device
that is present in the user’s home. It is triggered using
voice commands. Based on the request made, a response
will be returned to the user.
• Application Layer: This layer consists of the
following components:
1) Alexa Skills Kit (ASK) [12]-It is a minimalist
Software Development Kit (SDK) for developing ”skills”
for the Amazon Echo

2) Amazon Web Services(AWS)Lambda [14] -
Functionality that runs programs when invoked rather
than hosting programs on a server
• Programming Layer: The source codes of all our
programs are written in Python 2.7 and Node.js 4.3.
The technological stack is elaborated in the following
sections.
A. Devices
The input is given through Amazon's Echo. Echos
natural lifelike voices result from speech-unit selection
technology. It is able to perceive what the users are saying
using NLP algorithms built into the Echos text-to-speech
(TTS) engine. The Echo hardware complement includes a
Texas Instruments DM3725 ARM Cortex-A8 processor,
256MB of LPDDR1 RAM and 4GB of storage space. It
connects to the internet through WiFi 802.11a/b/g/n. The
Raspberry Pi serves as another I/O device. For this project,
we have used a Raspberry Pi 3 Model B, which uses a
Broadcom BCM2837 SoC with a 1.2 GHz 64-bit quad-core
ARM Cortex-A53 processor, with 512 KB shared L2 cache.
B. Infrastructure
Alexa voice services powers Amazon Echo by
converting speech into text and giving intelligent replies to
user requests. Alexa is capable of voice interaction, music
playback, making to-do lists, setting alarms, streaming
podcasts, playing audiobooks, and providing weather,
traffic and other real time information. Alexa can also
control several smart devices using itself as a home
automation hub. Amazon has released the 3 AVS API that
allows Alexa to integrate with devices and applications.
AWS Lambda is an event-driven, serverless computing
platform provided by Amazon. It is a compute service that
runs code in response to events and automatically
manages the compute resources required by that code. The
purpose of Lambda, as compared to AWS Elastic Compute
Cloud (AWS EC2)[15], is to simplify building smaller, on-
demand applications that are responsive to events and
new information. AWS targets starting a Lambda instance
within milliseconds of an event. Node.js, Python and Java
are all officially supported languages. Moreover, choosing
AWS Lambda is much more cost-efficient option in this
scenario.
C. Codebase
Node.js is used to seamlessly integrate AVS with
RaspberryPi. Node.js package system is called npm which
comes with a lot of libraries making it a very efficient and
flexible choice for programming. In addition to Node.js, we
have also used Python to build the Computer Vision
module. Python comes with inbuilt libraries that
manipulate images according to the users needs. There are
also many implementation of face detection algorithms in
python which utilises both complex algorithms like HOG to
simple ones like Haar Cascade. For coding this, we have
used Python 2.7 which has been a stable release since
2010.
IV.SYSTEM DESIGN
A. System overview
Our system as shown in Figure 1 - User, Raspberry
Pi and Alexa Voice Service. In this section, we will explain
briefly about each component's role to make the system
function.
B. Alexa Voice Service (AVS)
Alexa Voice Service is the intelligent voice control
service that powers the device, Amazon Echo. Alexa uses
natural language processing techniques trained by the
developers and the user community of Amazon to process
user requests and cater to their individual needs. The voice
service can be triggered using the keyword ”Alexa”. As
mentioned earlier, the skill/application that we have
developed can be triggered using the voice command,
”Alexa, Turn the lights on”. Once Alexa is triggered, it runs
a script on the cloud, which in-turn runs a subroutine on
the Raspberry Pi to Switch on the light. Once computation
is done in the Raspberry Pi, it sends the confirmation back
to Alexa. Only the essential information is sent to Alexa
which passes it on back to the user.
C. Raspberry Pi
Our application relies on Raspberry Pi as it
satisfies the hardware requirements and also does all the
computation. The Raspberry Pi has a WiFi and it will use
the relay to switch on and switch off the appliances.
Fig. 4. System Design

VI.TECHNOLOGIES USED
Platform and Language Used :
1) IoT platform for Pub Sub Services
2) Node.js
3) Linux based Raspbian OS (Jessey Debian)
VII.APPLICATIONS
As discussed in the earlier section even though there a
abundance of smart appliances available in the market
this is not feasible for the Indian market since it is very
expensive. Our product makes it viable for the market
since it is an easy and affordable and can be used with
any appliance.
CONCLUSION
The smart home space has a lot of interesting
challenges to be solved. One very important problem that
we tried to address in this paper is that of non-smart. We
made use of one of the hottest smart devices available
today in the market, Amazon Echo and coupled it with the
Raspberry Pi. The module we used for performing home
automation tasks worked well. Further, on testing the
application on Amazon Echo in real-time, we obtained
promising results. We believe that this a step towards a
cost-effective smart homes. We aim to build similar
applications in the future for Google Home and other
personal assistants that can revolve around using simple
voice commands to provide a cost effective solution for
non-smart homes.
REFERENCES
[1] https://ifttt.com/
[2] https://www.smartthings.com/
[3] https://my-digitallife.att.com/learn/explore-home-
automation
[4] https://madeby.google.com/home/
[5] https://www.raspberrypi.org/products/raspberry-pi-
3-model-b/
[6] https://developer.amazon.com/alexa-skills-kit
[7] https://firebase.google.com/
[8] https://aws.amazon.com/lambda/
[9] https://aws.amazon.com/ec2/

Voice Enabled Home Automation using Amazon Echo

More Related Content

Similar to Voice Enabled Home Automation using Amazon Echo (20)

More from IRJET Journal (20)

Recently uploaded (20)

Voice Enabled Home Automation using Amazon Echo