Gracenote, Inc.

In one aspect, an example computer-implemented method generating a pitch-based audio signature includes: (a) receiving audio content, (b) transforming the audio content, (c) generating a log-spaced frequency domain representation of the transformed audio content, (d) determining one or more magnitudes of the transformed audio content, (e) adjusting the log-spaced frequency domain representation of the transformed audio content based on the determined one or more magnitudes, (f) identifying a plurality of estimated pitch values within the adjusted log-spaced frequency domain representation, wherein identifying the plurality of estimated pitch values comprises identifying a plurality of peak characteristics in the adjusted log-spaced frequency domain representation and ordering the plurality of estimated pitch values based on the plurality of peak characteristics; and (g) generating the pitch-based audio signature based on the identified plurality of estimated pitch values.

Techniques of providing motion video content along with audio content are disclosed. In some example embodiments, a computer-implemented system is configured to perform operations comprising: receiving primary audio content; determining that at least one reference audio content satisfies a predetermined similarity threshold based on a comparison of the primary audio content with the at least one reference audio content; for each one of the at least one reference audio content, identifying motion video content based on the motion video content being stored in association with the one of the at least one reference audio content and not stored in association with the primary audio content; and causing the identified motion video content to be displayed on a device concurrently with a presentation of the primary audio content on the device.

A computing system automatically detects, within a digital video frame, a video frame region that depicts a textual expression of a scoreboard. The computing system (a) engages in an edge-detection process to detect edges of at least scoreboard image elements depicted by the digital video frame, with at least some of these edges being of the textual expression and defining alphanumeric shapes; (b) applies pattern-recognition to identify the alphanumeric shapes; (c) establishes a plurality of minimum bounding rectangles each bounding a respective one of the identified alphanumeric shapes; (d) establishes, based on at least two of the minimum bounding rectangles, a composite shape that encompasses the identified alphanumeric shapes that were bounded by the at least two minimum bounding rectangles; and (e) based on the composite shape occupying a particular region, deems the particular region to be the video frame region that depicts the textual expression.

A computing system determines accuracy of sport-related information extracted from a time sequence of digital video frames that represent a sport event, the extracted sport-related information including an attribute that changes over the time sequence. The computing system (a) detects, based on the extracted sport-related information, a pattern of change of the attribute over the time sequence and (b) makes a determination of whether the detected pattern is an expected pattern of change associated with the sport event. If the determination is that the detected pattern is the expected pattern, then, responsive to making the determination, the computing system takes a first action that corresponds to the sport-related information being accurate. Whereas, if the determination is that the detected pattern is not the expected pattern, then, responsive to making the determination, the computing system takes a second action that corresponds to the sport-related information being inaccurate.

Methods and systems for disambiguating musical artist names are disclosed. Musical-artist-release records (MARRs) may be input to a multi-modal artificial neural network (ANN). Each MARR may be associated with a musical release of an artist, and may include a release ID and an artist ID, and release data in categories including music media content and metadata categories including sub-definitive musician name of the artist and release subcategories. All n-tuples of MARRs may be formed, and for each n-tuple, the ANN may be applied concurrently to each MARR to generate a release feature vector (RFV) that includes a set of sub-feature vectors, each characterizing a different category of release data. For each n-tuple, the ANN may be trained to cluster in a multi-dimensional RFV space RFVs of the same artist ID, and to separate RFVs of different artist IDs. The MARRs and their RFVs may be stored in a release database.

Methods, apparatus, systems and articles of manufacture are disclosed for playback using pre-processed profile information and personalization. Example apparatus disclosed herein include a synchronizer to, in response to receiving a media signal to be played on a playback device, access an equalization (EQ) profile corresponding to the media signal; an EQ personalization manager to generate a personalized EQ setting; and an EQ adjustment implementor to modify playback of the media signal on the playback device based on a blended equalization generated based on the EQ profile and the personalized EQ setting.

Methods, apparatus, systems and articles of manufacture are disclosed to identify media based on historical data. An example method includes: comparing (a) a pitch shifted fingerprint, (b) a time shifted fingerprint, or (c) a resampled fingerprint to a reference fingerprint; in response to a match between any of (a) the pitch shifted fingerprint, (b) the time shifted fingerprint, or (c) the resampled fingerprint and the reference fingerprint, generating indications of (a) a pitch shift value, (b) a time shift value, or (c) a resample ratio that caused the match; in response to collecting broadcast media for a threshold period of time, processing the one or more indications; and in response to a request for a recommendation for information associated with a query, transmitting the recommendation including one or more frequencies of occurrence of (a) the pitch shift value, (b) the time shift value, or (c) the resample ratio.

In one aspect, a method includes detecting a fingerprint match between query fingerprint data representing at least one audio segment within podcast content and reference fingerprint data representing known repetitive content within other podcast content, detecting a feature match between a set of audio features across multiple time-windows of the podcast content, and detecting a text match between at least one query text sentences from a transcript of the podcast content and reference text sentences, the reference text sentences comprising text sentences from the known repetitive content within the other podcast content. The method also includes responsive to the detections, generating sets of labels identifying potential repetitive content within the podcast content. The method also includes selecting, from the sets of labels, a consolidated set of labels identifying segments of repetitive content within the podcast content, and responsive to selecting the consolidated set of labels, performing an action.

Example methods and systems for indexing fingerprints are described. Fingerprints may be made up of sub-fingerprints, each of which corresponds to a frame of the media, which is a smaller unit of time than the fingerprint. In some example embodiments, multiple passes are performed. For example, a first pass may be performed that compares the sub-fingerprints of the query fingerprint with every thirty-second sub-fingerprint of the reference material to identify likely matches. In this example, a second pass is performed that compares the sub-fingerprints of the query fingerprint with every fourth sub-fingerprint of the likely matches to provide a greater degree of confidence. A third pass may be performed that uses every sub-fingerprint of the most likely matches, to help distinguish between similar references or to identify with greater precision the timing of the match. Each of these passes is amenable to parallelization.

Methods, apparatus, systems and articles of manufacture are disclosed for efficient media indexing. An example method disclosed herein includes means for initiating a list of hash seeds, the list of hash seeds including at least a first hash seed value and a second hash seed value among other hash seed values, means for generating to generate a first bucket distribution based on the first hash seed value and a first hash function and generate a second bucket distribution based on the second hash seed value used in combination with the first hash seed value, means for determining to determine a first entropy value of the first bucket distribution, wherein data associated with the first bucket distribution is stored in a first hash table and determine a second entropy value of the second bucket distribution.