Methods and apparatus to identify and credit media using ratios of media characteristics are disclosed herein. Example methods and apparatus determine a first ratio based on a first combination of time intervals of a monitored media signature, the monitored media signature including a plurality of time intervals, respective ones of the time intervals being between respective adjacent characteristics identified in the media, determine a second ratio based on a second combination of time intervals of the monitored media signature, generate a monitored media ratio signature based on the first and second ratios, and compare the monitored media ratio signature with a reference ratio signature to identify the media.

Methods and apparatus to determine a state of a media presentation device are disclosed. Example disclosed methods include generating a first set of weighted coefficients based on first audio received by first and second microphones at a first time. Example disclosed methods include generating a second set of weighted coefficients based on second audio received by the first and second microphones at a second time after the first time. Example disclosed methods include comparing the first set of coefficients and the second set of coefficients to generate a similarity value. Example disclosed methods include, when the similarity value satisfies a threshold, determining that the media presentation device is in a first state. Example disclosed methods include, when the similarity value does not satisfy the threshold, determining that the media presentation device is in a second state.

A computing system receives from a media presentation device a query fingerprint stream representing media content being presented by the media presentation device, where the query fingerprint stream has been determined to represent a first channel. The computing system then detects that a threshold mismatch exists between the received query fingerprint stream and a reference fingerprint stream representing the first channel, thus indicating a likelihood that the media presentation device has transitioned from presenting the first channel to presenting a second channel. Responsive to detecting the threshold mismatch, the system thus discontinues channel-specific action with respect to the first channel. For instance, the system could discontinue superimposing of first-channel-specific content on the presented media content and perhaps start superimposing of second-channel-specific content instead.

A system and method for generating personalized multimedia content element clusters. The method includes determining, based on at least one interest, at least one personalized concept, wherein each personalized concept represents one of the at least one user interest; obtaining at least one multimedia content element related to a user; generating at least one signature for the at least one multimedia content element, each generated signature representing at least a portion of the at least one multimedia content element; determining, based on the generated at least one signature, at least one multimedia content element cluster, wherein each cluster includes a plurality of multimedia content elements sharing a common concept of the at least one personalized concept; and creating at least one personalized multimedia content element cluster by adding, to each determined cluster, at least one of the at least one multimedia content element sharing the common concept of the cluster.

Apparatus, methods, and articles of manufacture for encoding a compressed media stream are disclosed. Example method of watermarking a digital media signal disclosed herein include copying compressed audio packets associated with an audio stream included in a transport stream of the digital media signal into respective frames of compressed audio data to be watermarked to include media identification information. Such example methods can also include determining whether a composition of the transport stream has changed during copying of the compressed audio packets into the respective frames of the compressed audio data. Such example methods can further include, if the composition of the transport stream has changed, writing the frames of the compressed audio data to an output stream corresponding to the digital media signal without applying a watermark to the frames of the compressed audio data.

Example apparatus disclosed herein to implement signature matching with meter data aggregation for use in media identification applications include a match job aggregator to aggregate batches of meter data from a meter to form aggregated meter data associated with the meter, and a hash matcher to identify a valid hash key match between meter hash keys generated from meter signatures in the aggregated meter data and reference hash keys corresponding to a collection of media assets. Disclosed example apparatus also include a signature matcher to align, based on the valid hash key match, a sequence of reference signatures corresponding to a first media asset associated with the valid hash key match and a corresponding sequence of the meter signatures, and compare the sequence of reference signatures and the corresponding sequence of meter signatures to identify media represented by at least a portion of the sequence of the meter signatures.

A method and system for providing contextually appropriate overlays. The method includes causing the generation of at least one signature for each of at least one input multimedia content element, wherein each signature represents a concept, wherein each concept is a collection of signatures and metadata describing the concept; correlating the concepts represented by the generated signatures to determine at least one context of the at least one input multimedia content element; determining, based on the at least one context of the at least one input multimedia content element, at least one contextually relevant reference multimedia content element, wherein each contextually relevant multimedia content element has a context matching at least one of the determined at least one context above a predetermined threshold; and causing an overlay of the at least one contextually relevant reference multimedia content element on the at least one input multimedia content element.

A system and method for determining driving decisions based on multimedia content. The method includes obtaining, in real-time during a trip of a vehicle, trip multimedia content elements captured by at least one sensor deployed in proximity to the vehicle; identifying, based on at least one signature generated for each trip multimedia content element, at least one matching event multimedia content element, wherein each event multimedia content element demonstrates an event and is associated with a corresponding driving decision; and determining, in real-time, at least one driving decision, wherein each determined driving decision is associated with one of the identified at least one event multimedia content element.

A system and method for detecting one or more advertisements broadcast on a channel in real time includes a step of extracting a first set of audio fingerprints and a first set of video fingerprints. The first set of audio fingerprints and the first set of video fingerprints correspond to a media content broadcast on the channel. The method also includes a step of generating a set of digital signature values. The set of digital signature values corresponds to an extracted set of video fingerprints. The method also includes a step of detecting the one or more advertisements broadcast on the channel with the processor. The first set of video fingerprints and the audio fingerprints is extracted sequentially in the real time.

A system and method for searching based on input multimedia content elements. The method includes obtaining at least one signature for each of at least one input multimedia content element, each signature representing a concept, wherein each concept is a collection of signatures and metadata representing the concept; determining, based on the obtained signatures, at least one context of the at least one input multimedia content element; generating, based on the determined at least one context, at least one query; and searching in at least one data source using the generated at least one query.