Embodiments include apparatuses, systems, and methods for assisting in detection of user commands by virtual assistant devices. In embodiments, an apparatus for assisting or facilitating assistance to a user may include a first communication interface to receive an audio signal and a second communication interface to receive a modulated audio signal. In embodiments, a speech-recognition processor may be coupled to the first communication interface to detect a presence of a command in the audio signal. In embodiments, the command may include or be preceded by a keyword. In embodiments, a controller may be coupled to the second communication interface and the speech-recognition processor, to extract data from the modulated audio signal, and to dispose the detected command based at least in part on the data extracted on the modulated audio signal. Other embodiments may also be described and claimed.