Designing Android Applications Using Voice Controlled Commands: For Hands Free Interaction with Common Household Devices

Utilizing assistive technology to aid persons with neuromuscular disabilities, this study improves upon previously created offline voice control of household devices through an input-output peripheral interface control processor driven using an application on the Galaxy S Android smart phone. In trial, the most effective type of voice recognition software for offline communication was Pocketsphinx. This offline capability is used and tested for accuracy of several commands on a direct television remote though the exchange of Bluetooth signals between the phone (input) and transfer station (output). The application was designed to recognize key word commands and send signals to corresponding pins on the input-output board. The execution of a command was enabled through the interface of the smart phone with a television remote. In the laboratory, experiments were tested for accuracy taking into account distance between person and device as well as level of ambient noise and the vocalization of the subject.