Patents by Inventor Gheorghe Postelnicu

Gheorghe Postelnicu has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 9052986
    Abstract: Systems and methods are provided herein relating to audio matching. Both melody fingerprints and audio-id fingerprints can be used to improve an audio matching system's resistance to pitch shifts. A melody fingerprint can be used to identify a set of potential melody matches. Varying pitch shifted audio-id reference fingerprints can be generated for audio-id fingerprints associated with the potential matches identified in melody matching. Additional pitch shifted audio-id fingerprints of a reference sample are generated and used in matching only if an audio sample has previously been matched to a melody fingerprint of the same reference sample. A reference index need not be expanded to include pitch shifted variations of each reference sample as pitch shifted variations of audio-id fingerprint reference samples are generated and used only if their associated melody fingerprint is deemed a potential match.
    Type: Grant
    Filed: April 18, 2012
    Date of Patent: June 9, 2015
    Assignee: Google Inc.
    Inventors: Gheorghe Postelnicu, Matthew Sharifi
  • Patent number: 9031840
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving (i) audio data that encodes a spoken natural language query, and (ii) environmental audio data, obtaining a transcription of the spoken natural language query, determining a particular content type associated with one or more keywords in the transcription, providing at least a portion of the environmental audio data to a content recognition engine, and identifying a content item that has been output by the content recognition engine, and that matches the particular content type.
    Type: Grant
    Filed: December 27, 2013
    Date of Patent: May 12, 2015
    Assignee: Google Inc.
    Inventors: Matthew Sharifi, Gheorghe Postelnicu
  • Patent number: 9026540
    Abstract: Systems and methods described herein can assign a confidence score to a match of unstructured descriptive information with structured reference information in a reference database. The systems and methods can take into account the structured nature of the reference information in assigning the score, thereby facilitating increased confidence in the match, and consequently, facilitating improved database organization and content identification.
    Type: Grant
    Filed: January 31, 2012
    Date of Patent: May 5, 2015
    Assignee: Google Inc.
    Inventors: Gheorghe Postelnicu, Matthew Sharifi, Jay Michael Ponte, Yaniv Bernstein, Khalid Walid Abdel Monem Ashmawy
  • Patent number: 8953811
    Abstract: Systems and methods are provided herein relating to audio matching. A compact digest can be generated based on sets of triples, where triples are groupings of three interest points that meet threshold criteria. The compact digest can be used in identifying a potential audio match. A full digest can then be used in verifying the potential match. By using a compact digest to perform audio matching, the audio matching system can be scaled to encompass millions or billions of reference audio samples while still using the full digest to maintain accuracy.
    Type: Grant
    Filed: April 18, 2012
    Date of Patent: February 10, 2015
    Assignee: Google Inc.
    Inventors: Matthew Sharifi, Gheorghe Postelnicu, Sergey Ioffe
  • Patent number: 8953836
    Abstract: Systems and methods are provided herein relating to real-time duplicate detection of video content. Fingerprints can be generated for an uploaded video. The fingerprints can be used to match the uploaded video to a set of matching videos. The set of matching videos can be filtered based on the type of match, and the quality of the match. A unique cluster-id can be generated for the uploaded video containing an upload time, and that unique cluster-id can then be modified to associate the uploaded video with a cluster-id of potential duplicates. Cluster-ids can then be used in the context of a search to filter results that have identical cluster-ids. The benefits in using real-time duplicate detection can better maximize user experiences in a video sharing service that contains potential duplicates of the same content.
    Type: Grant
    Filed: January 31, 2012
    Date of Patent: February 10, 2015
    Assignee: Google Inc.
    Inventors: Gheorghe Postelnicu, Richard Iles Tucker, Murali Krishna Viswanathan, Nicola Muscettola, Varun Kacholia
  • Patent number: 8947595
    Abstract: A combined fingerprint is generated for a video that can match two near-identical videos that differ only in their aspect ratios or formats. A transformation strategy is selected by selecting a first and a second aspect correction method. A first transformed video is generated by applying the first aspect correction method to the video. A second transformed video is generated by applying the second aspect correction method to the video. A first fingerprint is generated using the first transformed video. A second fingerprint is generated using the second transformed video. The combined fingerprint is generated by combining the first half of the first fingerprint with the second half of the second fingerprint.
    Type: Grant
    Filed: December 9, 2010
    Date of Patent: February 3, 2015
    Assignee: Google Inc.
    Inventors: Richard Tucker, Henrik Rydgard, Gheorghe Postelnicu, Jasmine Kent, Michele Covell, Sergey Ioffe
  • Patent number: 8938089
    Abstract: Systems and methods are provided herein relating to real-time detection of inactive broadcasts during live stream ingestion. Both audio fingerprints and video fingerprints can be dynamically and continuously generated for a live stream ingestion. Sets of video fingerprints and sets of audio fingerprints can be continuously generated based on common successive overlapping time windows. A set of audio fingerprints and a set of video fingerprints can be associated with each time window. Video similarity scores and audio similarity scores can be generates for each time window to determine whether the stream is inactive or static during the time window. Only fingerprints relating to an active broadcast can be indexed in a fingerprint index.
    Type: Grant
    Filed: June 26, 2012
    Date of Patent: January 20, 2015
    Assignee: Google Inc.
    Inventors: Gheorghe Postelnicu, Matthew Sharifi
  • Publication number: 20150019612
    Abstract: Systems and methods are disclosed for providing device-specific instructions in response to a perception of a media content segment. In one implementation, a processing device captures, at a user device, one or more media content segments. The processing device provides the one or more media content segments to a remote device. The processing device receives one or more instructions, each of the one or more instructions being associated with at least one of the one or more media content segments and corresponding to one or more operations. The processing device initiates execution of at least one of the one or more instructions.
    Type: Application
    Filed: July 9, 2013
    Publication date: January 15, 2015
    Inventors: Matthew Sharifi, Gheorghe Postelnicu
  • Publication number: 20150019611
    Abstract: Systems and methods are disclosed for providing device-specific instructions in response to a perception of a media content segment. In one implementation, a processing device receives one or more media content segments from a user device. The processing device processes the one or more media content segments to determine one or more operations associated with the one or more media content segments. The processing device selects, based on one or more characteristics associated with the user device, at least one of the one or more operations. The processing device provides one or more instructions to perform the at least one of the one or more operations in relation to the user device.
    Type: Application
    Filed: July 9, 2013
    Publication date: January 15, 2015
    Inventors: Matthew Sharifi, Gheorghe Postelnicu
  • Patent number: 8918382
    Abstract: This disclosure relates to learning common spelling errors of metadata terms associated with content through content matching, such as content matching using fingerprints.
    Type: Grant
    Filed: May 8, 2013
    Date of Patent: December 23, 2014
    Assignee: Google Inc.
    Inventors: Matthew Sharifi, Gheorghe Postelnicu
  • Patent number: 8895830
    Abstract: Systems and methods are provided herein relating to interactive gaming within a media sharing service. Game data, such as sets of notes extracted from the audio track of user generated videos or from audio samples, can be generated based on videos containing musical content or from audio content. A device can use the game data to facilitate an interactive game during playback of the user generated videos or audio samples. Players can press buttons, for example, corresponding to notes as the video with musical content is played within the game interface. Players can be scored for accuracy, and can play with other players in a multiplayer environment. In this sense, user generated video content or audio content can be transformed and used within a gaming interface to increase interaction and engagement between users in a media sharing service.
    Type: Grant
    Filed: October 8, 2012
    Date of Patent: November 25, 2014
    Assignee: Google Inc.
    Inventors: Matthew Sharifi, Gheorghe Postelnicu, Aviv Reznik
  • Patent number: 8838609
    Abstract: Down scoring overcrowded bands via IDF weighting scores provides a soft way to reduce the effect of common bands from Locality Sensitive Hashing (LSH) processes. An index component indexes live video references of a live streaming infrastructure pathway process in a reference index. A scoring component scores a set of bands with a set of inverse document frequency (IDF) weighting scores in the reference index. A high score is generated for bands that are featured in a small number of references and a low score is generated for bands featured in a high number of references.
    Type: Grant
    Filed: October 10, 2012
    Date of Patent: September 16, 2014
    Assignee: Google Inc.
    Inventors: Matthew Sharifi, Gheorghe Postelnicu
  • Patent number: 8831763
    Abstract: System and methods for intelligently pruning interest points are disclosed herein. The systems include generating a plurality of distorted audio samples and associated distorted interest points based upon a clean audio sample. Interest points that are common to sets of distorted interest points are retained with interest points not robust to distortion discarded. The disclosed systems and methods therefore can provide for a scalable audio matching solution by eliminating interest points in reference sample fingerprints. The set of pruned interest points are robust to distortion and the benefits of both scalability and accuracy can be had.
    Type: Grant
    Filed: October 18, 2011
    Date of Patent: September 9, 2014
    Assignee: Google Inc.
    Inventors: Matthew Sharifi, Gheorghe Postelnicu, George Tzanetakis, Dominik Roblek
  • Patent number: 8738633
    Abstract: This disclosure relates to transformation invariant media matching. A fingerprinting component can generate a transformation invariant identifier for media content by adaptively encoding the relative ordering of interest points in media content. The interest points can be grouped into subsets, and stretch invariant descriptors can be generated for the subsets based on ratios of coordinates of interest points included in the subsets. The stretch invariant descriptors can be aggregated into a transformation invariant identifier. An identification component compares the identifier against a set of identifiers for known media content, and the media content can be matched or identified as a function of the comparison.
    Type: Grant
    Filed: January 31, 2012
    Date of Patent: May 27, 2014
    Assignee: Google Inc.
    Inventors: Matthew Sharifi, Sergey Ioffe, Jay Yagnik, Gheorghe Postelnicu, Dominik Roblek, George Tzanetakis
  • Patent number: 8726400
    Abstract: Systems and methods for detection and dispute management of claims made against proprietary content in a live data stream are provided in this disclosure. The system includes a reference stream generation component that updates a set of reference data streams based on an identification of data that is associated with non-live content (e.g., advertisements, flashbacks, etc.). Moreover, user generated content is compared with the set of reference data streams to facilitate identify the claims and a partner-defined policy is applied to the user generated content to facilitate dispute management and/or resolution.
    Type: Grant
    Filed: March 30, 2012
    Date of Patent: May 13, 2014
    Assignee: Google Inc.
    Inventors: Johan Georg Granström, Gheorghe Postelnicu, Oliver Markus Heckmann
  • Publication number: 20140114659
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving (i) audio data that encodes a spoken natural language query, and (ii) environmental audio data, obtaining a transcription of the spoken natural language query, determining a particular content type associated with one or more keywords in the transcription, providing at least a portion of the environmental audio data to a content recognition engine, and identifying a content item that has been output by the content recognition engine, and that matches the particular content type.
    Type: Application
    Filed: December 27, 2013
    Publication date: April 24, 2014
    Applicant: Google Inc.
    Inventors: Matthew Sharifi, Gheorghe Postelnicu
  • Publication number: 20140074466
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving audio data encoding an utterance and environmental data, obtaining a transcription of the utterance, identifying an entity using the environmental data, submitting a query to a natural language query processing engine, wherein the query includes at least a portion of the transcription and data that identifies the entity, and obtaining one or more results of the query.
    Type: Application
    Filed: September 25, 2012
    Publication date: March 13, 2014
    Applicant: Google Inc.
    Inventors: Matthew Sharifi, Gheorghe Postelnicu
  • Publication number: 20140074474
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving (i) audio data that encodes a spoken natural language query, and (ii) environmental audio data, obtaining a transcription of the spoken natural language query, determining a particular content type associated with one or more keywords in the transcription, providing at least a portion of the environmental audio data to a content recognition engine, and identifying a content item that has been output by the content recognition engine, and that matches the particular content type.
    Type: Application
    Filed: February 15, 2013
    Publication date: March 13, 2014
    Applicant: Google Inc.
    Inventors: Matthew Sharifi, Gheorghe Postelnicu
  • Patent number: 8655657
    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving (i) audio data that encodes a spoken natural language query, and (ii) environmental audio data, obtaining a transcription of the spoken natural language query, determining a particular content type associated with one or more keywords in the transcription, providing at least a portion of the environmental audio data to a content recognition engine, and identifying a content item that has been output by the content recognition engine, and that matches the particular content type.
    Type: Grant
    Filed: February 15, 2013
    Date of Patent: February 18, 2014
    Assignee: Google Inc.
    Inventors: Matthew Sharifi, Gheorghe Postelnicu
  • Patent number: 8625033
    Abstract: Large-scale matching of videos is performed by matching a set of probe videos against a set of reference videos to determine if they are visually and/or aurally similar. The visual and audio fingerprints of all probe videos and reference videos are divided into subfingerprints, which are divided into LSH bands. The LSH bands of the probe videos are sorted in one list, and the LSH bands of the reference videos are sorted in another list. Then, the two sorted lists are linearly scanned for matching LSH bands. The matching LSH bands are sorted by probe video ID, and each probe video ID is searched to find matches between probe videos and reference videos. Further, an incremental matching process identifies matches as groups of new probe videos and/or new reference videos are added, without unnecessary repetition of matching old probe videos against old reference videos.
    Type: Grant
    Filed: February 1, 2010
    Date of Patent: January 7, 2014