Abstract: An automated content recognition (ACR) system can identify media based on audio-related data. For instance, the ACR system may receive an audio cue associated with an unknown media segment. The audio cue can include a set of words derived from the unknown media segment. The ACR system can search a known media database using the set of by comparing the set of words with words associated with known media segments. The ACR system may identify a particular known media segment from the known media database that at least partially matches the set of words of the unknown media segment. In some implementations, the ACR system may execute an event in response to identifying the unknown media segment.

Abstract: An automated content recognition system can identify media presented by a media device using an audio channel of the media. The media device may isolate an audio segment from the audio channel of the media. A speech-to-text model may be executed using the audio segment to identify a sequence of words represented by the audio segment. The media device may transmit an unknown audio including the sequence of words to an ACR server. The ACR server may compare the sequence of words of the unknown audio cue to words of reference audio cues associated with known media segments.