A method and system for improving audio detection is provided. The method includes receiving activation term data and text data of a multimedia file. The text data is analyzed and potential phonetic matches between a set of terms and the activation term are determined. An audio portion of the multimedia file is analyzed with respect to the potential phonetic matches and a resulting subset of terms is determined. A term is selected from the subset and flagged. An associated control action for preventing an automated device from being enabled is generated and stored. Presentation of the flagged term is detected within the multimedia file being presented and the control action is executed such that the automated device remains in the deactivated state.