A voice recognition device and method allows position-stabilized capture of spoken sounds with great repeatability and accuracy. The voice recognition device may additionally provide two channels of lip movement information to supplement the usual audible speech component recognition system in selecting the proper pairing of data input to text output. The voice recognition device may provide a further channel of information about the speech generating motions via an ultrasonic injection of sound into the vocal cavity and subsequent decoding of the emitted sound after injection. The ultrasonic injection and decoding may also used to provide audible clues as to the unvoiced sound formed by speaking when the vocal cords are not energized. The ensemble of electronic equipment upon the bail band may be in microcircuit form, including placing the components on a copper layer polyimide flexible strip. The side camera and “other side” illuminator LED may be on thin copper polyimide strips attached to the main electronics ensemble, and a set of thin polyimide conductors would conduct power into the ensemble and the signals out of the ensemble through one of the bail band ends, into the ear piece and down the connector to the associated computer equipment and may also supply the power for the electronic ensemble. The electronic ensemble may be potted with a thin layer of elastomer, such as translucent silicone, and provide a moisture barrier and physical protection for the ensemble, while still offering a very light visual weight to the combination of the electronic ensemble and the bail band.