In general, embodiments of the present disclosure are directed to techniques for determining a user's potential exposure to defined audio content (e.g., television and audio advertisements) using a mobile device. In one example, a method includes receiving first audio content. The method further includes generating a first digital representation of the first audio content. The method also includes accessing a data structure, wherein the data structure contains at least a second digital representation of at least second audio content. The method also includes comparing the first digital representation to at least the second digital representation contained in the data structure and if there is a match between the first digital representation and at least the second digital representation contained in the data structure, transmitting a message to a remote server indicating the match.