Speech recognition based wireless automation of home loads with fault identification for physically challenged

摘要

The design of this project helps in providing a fool proof solution for physically challenged to control their home appliances by giving voice commands through personal computer in a wireless environment. 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 or undergone FAULT by getting the status from load end, unlike the other design that gets the status at user end which may give a false indication, when power supply is not available for the particular load or when load get open circuited (due to wire discontinuity or open fuse condition). During user screen navigation and controlling home appliances voice output of the current screen information and status of the automated appliances enables visually impaired person to use the system to control their home appliances. Navigation of the screen by giving voice commands enables paralyzed person and person who lost their hands in an unfortunate accident to control their home loads along with normal person. For achieving wireless environment low cost zigbee is used. To provide security based authentication RFID is used. Each home load will be having two commands ON and OFF commands, Automation of 20 loads such as mixer, grinder, TV, refrigerator, fan, light, AC etc…, has been tested by giving 40 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.