Respirator acoustic amelioration

An acoustic signal is received from a first user. The acoustic signal of the first user includes a verbal utterance related to the first user. A set of one or more non-verbal sensor readings may be detected from a set of one or more sensors of a wearable device. The wearable device is worn by the user concurrent with the verbal utterance. A verbal distortion factor may be determined based on an acoustic adjustment model and in response to the set of non-verbal sensor readings. An adjusted verbal utterance related to the first user may be generated. The adjusted verbal utterance may be generated from the verbal utterance and based on the verbal distortion factor. The adjusted verbal utterance may be provided to a voice output.