Abstract:
Home automation system has gained popularity nowadays. Considering this, we have developed a home automation system based on voice control. There are many advanced voice-controlled home automation systems like “Alexa” from Amazon, “Cortana” from Microsoft, and “Google Home” from Google available in the market but there is no machine learning approach based on machine learning which works on the CNN algorithm. This can greatly improve the convenience and efficiency of managing a home, as it allows users to control various devices and systems remotely and automate certain tasks. The accuracy of CNN is very high so we have worked on this algorithm to recognize voice commands. The system uses natural language processing techniques to interpret user inputs and perform corresponding actions on connected devices. Many algorithms work on speech recognition like VAD, SBN, PLP features, Deep neural networks, discrimination training, and WFST framework but we thought that CNN with ML will deliver more accurate results in this field. We have collected our voice dataset from the internet & processed using Python & ML. After everything, we got 81% accuracy of that dataset but we think that we can get more optimal results in the future if we can do proper use of this algorithm & ML.
