Abstract: An example method includes receiving queries from devices that include respective samples of content from a stream of content rendered by a source, receiving samples of content from a stream of content rendered by an alternative feed of the source, and for each sample of content from the alternative feed of the source, identifying respective matching queries that match to the same content as the sample of content from the alternative feed of the source. The method also includes for each respective matching query, determining a respective relative time difference between a time that the content appears in the sample of content from the alternative feed and a time that the content appears in the respective matching query, accumulating a distribution of the time differences over time, and determining a latency between the source and the alternative feed of the source.

Abstract: A system and method are described for recognizing repeated audio material within at least one media stream without prior knowledge of the nature of the repeated material. The system and method are able to create a screening database from the media stream or streams. An unknown sample audio fragment is taken from the media stream and compared against the screening database to find if there are matching fragments within the media streams by determining if the unknown sample matches any samples in the screening database.