Abstract—Sound intelligence is added to a home automation based on acoustics for sophistication of physically challenged people as a broad perspective of the thesis. Home automation already in practice is by switching on or off a device via wired networks. But this is inefficient for people with impairment in mobility or spinal cord disability due to ageing factors. The easiest way of controlling a device is through human voice. Existing products are expensive and also speech recognition is available with usage of internet (online). This paper is presented with the concept of speech recognition being implemented using Hidden Markov Model Toolkit (HTK) in an offline manner (without internet). Human voice is converted to text using HTK and it is wirelessly Trans received using GSM modems. According to the received texts appliances can be controlled. The module contains a secured speech recognizer for automatic door opening/closing and a general voice recognizer to control appliances like television, music player, fan, light, etc. All the above are implemented in a low cost Raspberry Pi board. Thus a goal of producing an automation device has been designed at low cost using offline speech recognition [1].

 

Index Terms—HTK, SPHINX, RASPBERRY PI term

Cite: Prasanna G. and Ramadass N., "Low Cost Home Automation Using Offline Speech Recognition," International Journal of Signal Processing Systems, Vol. 2, No. 2, pp. 96-101, December 2014. doi: 10.12720/ijsps.2.2.96-101