978-1-5090-4642-3/17/$31.00 ©2017 IEEE Automatic Home Appliance Switching Using Speech Recognition Software and Embedded System Kennedy Okokpujie, Etinosa Noma-Osaghae, Samuel John, Prince C. Jumbo Department of Electrical and Information Engineering Covenant University, Ota Ogun State, Nigeria kennedy.okokpujie, etinosa.noma-osaghae, samuel.john, (@covenantuniversity.edu.ng) Abstract— In most homes, electrical appliances are controlled and operated manually, this could be difficult and challenging to do when tiredness, handicap, morphological variations (height, aging etc.) and inadequate skill stands in the way as impediment. This study aims to implement a better and more flexible means of controlling home appliances by means of an automated switching mechanism using speech recognition technique. Acoustic signals picked by a microphone controlled by a speech recognition application generate digital signals that are passed to a microcontroller, which in turn dispatches commands that operate the relays to which the appliances in the home are connected. The goal of using speech command to automate the switching of home appliances was achieved and proved to be a more convenient means of switching home appliances. Keywords—embedded system; speech; switching; andriod; relays; phonemes. I. INTRODUCTION For some time humans have aspired to create “Smart machines” which can master the natural speech. This system usually should consist of speech recognition and hardware controlling parts. Speech is an effective way of communicating and ideas could be narrated with relative ease. At the time personal computers were invented, achieving the level of complexity that can relate speech commands to a machine was only a form of science fiction. However with breakthroughs in the field, we are at the stage of truly using speech to interface with devices. Modern homes today have customized audio theaters, television, electronic lamps, closed circuit television, air conditioners etc. installed in them. The use of speech recognition technology greatly improves the usability and functionality of any modern home [2]. Automating the switching of home appliances using speech recognition technique has lower power consumption and savings in monetary terms as its hallmark. The use of speech to automate the control home appliances can be wired or wireless. The main difference being in the way the home appliances are connected. In the former, home appliances are connected to a central controller but in the latter, they are linked wirelessly. This system provides consumers with increased economic benefit through convenience by giving them remote control over the switching of every piece of electrical equipment in the house. Automatic control using speech recognition technology is the process by which a machine or program receives and interprets dictation as well as understands and carries out spoken commands. The process is highly beneficial because it provides a natural and intuitive way of controlling household appliances using speech instead of the hands. Several works have been done on possible remote access approaches for controlling devices thereby providing remote access of home appliances to its owners. This paper concerns itself with the design and implementation of a smart house remote control using software applications interacting with the speech recognition and network actuating system [1]. The analog to digital converter converts the speech signal into digital signal for the computer. The analog to digital converter digitizes the speech signal. This digitized signal is filtered and the noise removed [16]. While filtering, the speech signal is separated into its different bands of frequency and normalized (matching of the speech signal to the speech template stored in the memory of the system for varying speaking speeds). The normalized speech signal is divided into smaller segments and matched with known phonemes. A program finally determines the words being said by the user and displays the output as text and issues a command. This command is sent to the microcontroller, which switches the specified home appliance(s) on or off. II. RELATED STUDIES A. An overview of speech recognition systems Speech recognition is a technology that enables a computer to capture the words spoken by a human with a help of a microphone [1] [2]. The process of speech recognition consists of different steps that will be discussed in the following sections one by one. An ideal situation in the process of speech recognition is that, a speech recognition engine recognizes all words uttered by a human but, practically the performance of a speech recognition engine depends on a number of factors. Vocabularies, multiple users and noisy environments are the major factors that affect the performance of speech recognition systems.