A user wearing headphones (e.g., to listen to music, to engage in a voice call, etc.) may speak while receiving an audio signal through the headphones, which may cause the user to produce Lombard speech. Because the Lombard effect is generally involuntary, the user may be unaware that he or she is producing Lombard speech. The Lombard speech may inconvenience proximate individuals and/or embarrass the user (e.g., in an office, in an airport, etc.). An apparatus may be configured to receive, through a microphone communicatively coupled to the apparatus, an audio signal. The apparatus may be configured to determine whether the audio signal indicates speech by a user. The apparatus may be further configured to alert the user based on the determination that the audio signal indicates Lombard speech by the user.