System and method for speech detection

A system comprising:

• a microphone structured to measure an audio signal comprising a background noise component in an acoustic environment of a user;
• and
• a headset communicatively coupled to the microphone, comprising:
• a housing arranged at an auricular region of the user;
• a set of sensors arranged in the housing, directed toward a measurement region of the user, wherein the set of sensors is configured to sample biophysical signals from the measurement region;
• a processor comprising a model trained to
• a) determine a set of linguistic units based on a set of subvocal speech signals indicative of parameters of a set of speech articulators of the user and
• b) perform a noise reduction process in response to a background noise component of the audio signal exceeding a predetermined threshold, wherein:
• the set of subvocal speech signals comprise biophysical signals sampled using the set of sensors, and
• the noise reduction process comprises using the set of linguistic units to remove the background noise component from the audio signal.