Boliven Subscriptions: buy a subscription to Boliven and access advanced analytics and complete databases. Find out more »

Welcome to Boliven.com, the leading portal for R&D, business development and IP professionals

Free & easy searching » Analyze & Download search results » Work collaboratively with colleagues » We keep you updated »


Click here to Sign Up. It's Free To Join.

US7516074: Extraction And Matching Of Characteristic Fingerprints From Audio Signals

Filing Information

Inventor(s) Sergiy Bilobrov ·
Assignee(s) Auditude, Inc. ·
Attorney/Agent(s) Fenwick & West LLP ·
Primary Examiner Susan McFadden ·
Application Number US11219385
Filing date 09/01/2005
Issue date 04/07/2009
Prior Publication Data
Predicted expiration date 10/16/2027
Patent term adjustment 775
U.S. Classifications 704/270  ·
International Classifications G10L 21/00  ·
Kind CodeB2
48 Claims, 4 Drawings


Abstract

An audio fingerprint is extracted from an audio sample, where the fingerprint contains information that is characteristic of the content in the sample. The fingerprint may be generated by computing an energy spectrum for the audio sample, resampling the energy spectrum logarithmically in the time dimension, transforming the resampled energy spectrum to produce a series of feature vectors, and computing the fingerprint using differential coding of the feature vectors. The generated fingerprint can be compared to a set of reference fingerprints in a database to identify the original audio content.

Independent Claims | See all claims (48)

  1. 1. A method for extracting an audio fingerprint from an audio frame, the method comprising: filtering the audio frame into a plurality of frequency bands to produce a corresponding plurality of filtered audio signals; resampling the filtered audio signals at a nonlinear timescale; transforming the resampled audio signals for each frequency band to produce a feature vector for the frequency band; and computing the audio fingerprint based on the set of feature vectors.
  2. 26. A method for extracting an audio fingerprint from an audio frame, the method comprising: a step for computing a spectrogram for the audio frame; sampling the spectrogram at a nonlinear time scale for a plurality of frequency bands in the spectrogram; a step for extracting a long-term feature vector using the samples from each of the sampled frequency bands; and a step for generating the audio fingerprint based on the feature vectors.
  3. 28. A computer program product for extracting an audio fingerprint from an audio frame, the computer program product comprising a computer-readable medium containing computer program code for performing the method comprising: filtering the audio frame into a plurality of frequency bands to produce a corresponding plurality of filtered audio signals; resampling the filtered audio signals at a nonlinear timescale; transforming the resampled audio signals for each frequency band to produce a feature vector for the frequency band; and computing the audio fingerprint based on the set of feature vectors.

References Cited

U.S. Patent Documents

Document NumberAssigneesInventorsIssue/Pub Date
US5918223 Muscle Fish Blum et al. Jun 1999
US6266003 Sigma Audio Research Limited Hoek Jul 2001
US6453252 Creative Technology Ltd. Laroche Sep 2002
US6990453* Landmark Digital Services LLC Wang et al. Jan 2006
US7328153* Gracenote, Inc. Wells et al. Feb 2008
US7346512* Landmark Digital Services, LLC Wang et al. Mar 2008
US20020072982 Shazam Entertainment Ltd. Barton et al. Jun 2002
US20020083060 Wang et al. Jun 2002
US20020161741 Shazam Entertainment Ltd. Wang et al. Oct 2002
US20030086341 GRACENOTE, INC. Wells et al. May 2003
US20060072786 Kaleidescape, Inc. Watson et al. Apr 2006
US20060075237 Koninklijke Philips Electronics N.V. Seo et al. Apr 2006
US20060080356 Microsoft Corporation Burges et al. Apr 2006

Foreign Patent Documents

Document NumberAssigneesInventorsIssue/Pub Date
WO200120483CANTAMETRIX, INC.Mar 2001
WO200120609CANTAMETRIX, INC.Mar 2001
WO200162004AUDIBLE MAGIC CORPORATIONAug 2001
WO200176290MOBIQUIDOct 2001
WO200227600SHAZAM ENTERTAINMENT LTD.Apr 2002
WO200237316AUDIBLE MAGIC CORPORATIONMay 2002
WO200211123SHAZAM ENTERTAINMENT LIMITEDJul 2002
* cited by examiner

Other Publications

Foote, J. “Content-based Retrieval of Music and Audio”, in Multimedia Storage and Archiving Systems II, Proc. Of SPIE, C.C. J. Kuo et al., Eds., 1997, vol. 3229, pp. 138-147.
Lin, K. et al.: The TV-tree: An Index Structure for High Dimensional Data. VLDB Journal, pp. 517-541 (1992).
Zhang, T. et al.: Content-based Classification and Retrieval of Audio. In: SPIE's 43rd Annual Meeting—Conf. On Advanced Signal Processing Algorithms, Architectures, and Implementations VIII, SPIE vol. 3461, San Diego, Jul. (1998) 432-443.
TRM Advanced Audio Fingerprinting from Relatable. Retrieved from internet at http://relatable.com/tech/trm.html (2002).
Content-Based Classification, Search, and Retrieval of Audio: Free article by Muscle Fish in IEEE MultiMedia, retrieved from internet at: http://audiblemagic.com/solutions/ieee-1.htm (2002).
Sukittanon, Somask et al., Modulation Scale Analysis for Content Identification, UWEE Technical Report No. UWEETR-2003-0025, Department of EE, University of Washington, Nov. 1, 2003, 11 pages.
Haitsma, Jaap et al., A Highly Robust Audio Fingerprinting System, Proceedings of ISMIR 2002. Paris, France, Oct. 2002, 9 pages.
Sukittanon, Somsak, Modulation-Scale Analysis for Content Identification, IEEE Transactions on Signal Processing. vol. 52, No. 10, Oct. 2004, pp. 3023-3035.
Seo, Jin Soo, Linear Speed-Change Resilient Audio Fingerprinting, Proc. 1st, IEEE Benelux Workshop on Model Based Processing and Coding of audio (MPCA-2002), Leuven, Belgium, Nov. 15, 2002, pp. 45-48.
Haitsma, J.A., A new Technology to Identify Music, Nat. Lab. Unclassified Report 2002/824, Aug. 13, 2002, 30 pages.

Patent Family

The current document is not in a family.

Page actions


Searchable
PDF
Add to
my lists

Save

Save Item
Share
Share On Linked In Share On Facebook Share On Twitter Share By Email

Reports


Blood Glucose Monitors and Wireless Communication
Telehealth

more
Recent Trends in Nanotechnology Patenting: 2005 to May 2011
Nano1

more
First Solar, Inc. (Nasdaq: FSLR) - A Focus on the Technology Fundamentals
Solar

more
Patenting flatland: Graphene - Exploitation challenges and opportunities
Graphene_patent_landscape_report

more
Patenting Flatland: Graphene
Naturereport2

more
Pandemic Influenza (H1N1 & H5N1) patenting trends
Hn51

more