Iheartmedia Management Services, Inc.

Clear Channel Management Sevices, Inc.

Dyon Anniballi

Philippe Generali

A media item included in a broadcast is identified by receiving, at a processing device including a processor, a first recorded representation of a first media broadcast, which includes a recording of at least a portion of a first media item, via a known media station. The first recorded representation. An identity of the first media item is determined based on a broadcast schedule associated with the known media station. A second recorded representation of a second media broadcast transmitted via an unknown media station, which includes a recording of at least a portion of a media-item-of-interest is also received at the processing device. The media-item-of-interest is identified by the processing device based on a block-by-block comparison of the first recorded representation to the second recorded representation. The comparison includes comparing first blocks included in the first recorded representation against second blocks included in the second recorded representation on a frame by frame basis.

Automated media identification using block comparisons of different recorded representations

A computing system includes an interface configured to interface and communicate with an external media resource, a memory that stores operational instructions and a processing module operably coupled to the interface and to the memory, such that the processing module, when operable within the computing system based on the operational instructions, is configured to is configured to perform various operations. The computing system receives an audio fingerprint from the external medial resource, divides the audio file segment into a plurality of portions and compares the audio file segment with a plurality of stored audio segments. The computing system then determines whether a threshold number of the plurality of portions of a stored audio segment compare favorably with a threshold number of the plurality of portions of the audio file segment and based thereon determines whether the audio file segment and the stored audio segment correspond to alternate versions of a same song.

System for matching alternate versions of a song

A computing system includes an interface configured to interface and communicate with an external media resource, a memory that stores operational instructions and a processing module operably coupled to the interface and to the memory, such that the processing module, when operable within the computing system based on the operational instructions, is configured to is configured to perform various operations. The computing system receives an audio fingerprint from the external medial resource, compares the received audio fingerprint with a stored audio fingerprint and in response to determining that a portion of a stored audio fingerprint substantially matches a portion of the received audio fingerprint, compares a first set of consecutive portions of of the received audio fingerprint to each of a plurality of consecutive portions of the stored audio fingerprint to generate corresponding match scores. The computing system identifies a longest unordered match as a number of consecutive portions of the first set that each have a corresponding highest match score satisfying a similarity threshold and when the longest unordered match compares favorably to a length criterion, determines a match between the received audio fingerprint and the stored audio fingerprint.

System for matching media files

Automated data-matching includes obtaining first and second stored fingerprints generated from first and second data. The stored fingerprints are divided into frames, and grouped into first blocks and second blocks including an equal number of frames. Each frame included in a current first block is compared to each frame included in a current second block to determine a number of matching frames, and a hamming distance between the current first block and the current second block is determined, based at least in part on the number of matching frames. A determination is made, based at least in part on the hamming distance, whether the current first block and the current second block match.

Automated data-matching based on fingerprints

Broadcast signatures (fingerprints) from different sources are compared to distinguish between a known base media item and unknown versions of the known base media item, without prior storage of the unknown altered versions of the known base media item. Field recorders collect and store in buffers signatures found within portions of sequential broadcast content. Mobile devices (users) collect unknown signatures while recording broadcast content. Using a cloud callout routine, the mobile device requests a comparison between the collected unknown signatures and the field recorded signatures. Potential matches can be loose matches, strict matches or comparisons between failed loose comparisons.

Cloud callout identification of unknown broadcast signatures based on previously recorded broadcast signatures

A method includes computing match scores for each portion of multiple portions of a first audio fingerprint. The match scores are based on a comparison of the portion with each of multiple portions of a second audio fingerprint. The method includes generating a list of runs based on the highest score for each portion of the multiple portions of the first audio fingerprint. The method includes determining, based on the list of runs, an unordered match between a set of consecutive portions of the first audio fingerprint and a set of non-consecutive portions of the second audio fingerprint. The method includes, in response to determining that a position threshold of the unordered match satisfies a position criterion, outputting an indicator that the first audio fingerprint matches the second audio fingerprint.

Unordered matching of audio fingerprints

First fingerprint data is accumulated in a first fingerprint buffer of a channel identification server in parallel with accumulation of second fingerprint data in a second fingerprint buffer of the channel identification server. The first and second fingerprint data include multiple fingerprints representing broadcast content broadcast by corresponding broadcast sources during contiguous time periods, and accumulating the fingerprints includes appending newly received first fingerprints to previously received first fingerprints to generate continuous fingerprints. The channel identification server also receives an unmatched fingerprint representing broadcast content received from an unknown broadcast source by the end-user device. The unmatched fingerprint into probes, which are scrubbed against both first and second continuous fingerprints in an attempt to determine a match between the unmatched fingerprint and either the first or second continuous fingerprint. The unknown broadcast source is identified based on that determination.

Source identification using parallel accumulation and comparison of broadcast fingerprints

A method includes computing match scores for each portion of multiple portions of a first audio fingerprint. The match scores are based on a comparison of the portion with each of multiple portions of a second audio fingerprint. The method includes generating a list of runs based on the highest score for each portion of the multiple portions of the first audio fingerprint. The method includes determining, based on the list of runs, an unordered match between a set of consecutive portions of the first audio fingerprint and a set of non-consecutive portions of the second audio fingerprint. The method includes, in response to determining that a length of the unordered match satisfies a length criterion, outputting an indicator that the first audio fingerprint matches the second audio fingerprint.

Small changes in a broadcast version of a base media item can be identified by performing a multi-level comparison of digital fingerprints. A fingerprint of a base media item is compared to a fingerprint of a media broadcast to determine whether a media item embedded in a broadcast is likely, to a first level of certainty, to be the base media item. A second, more stringent, match between the fingerprint of the base media item and loosely matched items can be used to identify potentially-altered versions of the base media item. Potentially-altered versions can be compared against each other, and resulting matches are flagged as altered base media items, which can be fingerprinted and tested against broadcast fingerprints in the same manner as the base media item. Comparisons are made in parallel between two fingerprints to distinguish between a known base media item and unknown altered versions of the known base media item without prior storage of the unknown altered versions of the known base media item.

Identification of unknown altered versions of a known base media item

A method includes computing match scores for each portion of multiple portions of a first audio fingerprint. The match scores are based on a comparison of the portion with each of multiple portions of a second audio fingerprint. The method includes applying a positional penalty to a highest score of the match scores for a portion of the first audio fingerprint and generating a list of runs based on the highest score for each portion of the multiple portions of the first audio fingerprint. The method includes determining, based on the list of runs, an unordered match between a set of consecutive portions of the first audio fingerprint and a set of non-consecutive portions of the second audio fingerprint. The method includes, in response to determining that a length of the unordered match satisfies a length criterion, outputting an indicator that the first audio fingerprint matches the second audio fingerprint.

An end user can sample a radio or television broadcast, generate a user representation of the broadcast sample, and send the user representation to a comparison system, which also receives known representations of content broadcast by multiple different stations. The known representations are stored in a continuous fashion, and represent actually broadcast content. The comparison system identifies the source of the broadcast sample by comparing the user representation to the known representations associated with each of the different stations using a bit count method, such as the Hamming distance. By comparing two representations of content that was actually broadcast, a broadcast source can be identified without requiring the use of watermarks, timestamps, or a database of discreet content items.

Identification of broadcast source associated with unknown fingerprint

Small changes in a broadcast version of a base media item can be identified by performing a multi-level comparison of digital fingerprints. A fingerprint of a base media item is compared to a fingerprint of a media broadcast to determine whether a media item embedded in a broadcast is likely, to a first level of certainty, to be the base media item. A second, more stringent, match between the fingerprint of the base media item and loosely matched items can be used to identify potentially-altered versions of the base media item. Potentially-altered versions can be compared against each other, and resulting matches are flagged as altered base media items, which can be fingerprinted and tested against broadcast fingerprints in the same manner as the base media item.

Parallel identification of media source

A method includes determining, at a processor of a device, an unordered match between a set of consecutive portions of a first audio fingerprint and a set of non-consecutive portions of a second audio fingerprint. The method also includes setting, based at least in part on a station associated with the second audio fingerprint, a length criterion to indicate a first length or a second length. The method further includes, in response to determining that a length of the unordered match satisfies a length criterion, outputting an indicator that the first audio fingerprint matches the second audio fingerprint.

A method includes determining, at a processor of a device, an unordered match between a set of consecutive portions of a first audio fingerprint and a set of non-consecutive portions of a second audio fingerprint. The method also includes, in response to determining that a length of the unordered match satisfies a length criterion, outputting an indicator that the first audio fingerprint matches the second audio fingerprint.

Growing community of inventors

Wayne, PA, United States of America

Dyon Anniballi