US 12,405,999 B2
Matching audio fingerprints
Robert Coover, Orinda, CA (US); Jeffrey Scott, Berkeley, CA (US); and Konstantinos Antionios Dimitriou, Bavaria (DE)
Assigned to Gracenote, Inc., New York, NY (US)
Filed by Gracenote, Inc., Emeryville, CA (US)
Filed on Feb. 16, 2024, as Appl. No. 18/443,911.
Application 18/443,911 is a continuation of application No. 17/187,431, filed on Feb. 26, 2021, granted, now 11,954,148.
Application 17/187,431 is a continuation of application No. 15/115,733, granted, now 10,936,651, issued on Mar. 2, 2021, previously published as PCT/US2016/044041, filed on Jul. 26, 2016.
Prior Publication US 2024/0202237 A1, Jun. 20, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/63 (2019.01); G06F 16/61 (2019.01); G06F 16/65 (2019.01); G06F 16/683 (2019.01)
CPC G06F 16/683 (2019.01) [G06F 16/61 (2019.01); G06F 16/63 (2019.01); G06F 16/65 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
generating a query fingerprint that includes query sub-fingerprints generated from query segments of a portion of query audio;
accessing an index, wherein the index maps reference sub-fingerprints generated from reference segments of audio to points at which the reference segments occur in the audio;
generating a count vector, wherein the count vectors stores total counts of matches between the query sub-fingerprints and a plurality of subsets of the reference sub-fingerprints, wherein each of the plurality of subsets are aligned to the query sub-fingerprints at a different offset from a reference point;
calculating a difference between: (i) a maximum count of the total counts stored in the count vector; and (ii) a median of the total counts in the count vector; and
classifying the reference sub-fingerprints as a match with the query sub-fingerprints based on the calculated difference between the maximum count in the count vector and the median of the total counts.