US 11,810,559 B2
Unsupervised keyword spotting and word discovery for fraud analytics
Hrishikesh Rao, Atlanta, GA (US)
Assigned to PINDROP SECURITY, INC., Atlanta, GA (US)
Filed by Pindrop Security, Inc., Atlanta, GA (US)
Filed on Jun. 6, 2022, as Appl. No. 17/833,674.
Application 17/833,674 is a continuation of application No. 16/775,149, filed on Jan. 28, 2020, granted, now 11,355,103.
Claims priority of provisional application 62/797,814, filed on Jan. 28, 2019.
Prior Publication US 2022/0301554 A1, Sep. 22, 2022
Int. Cl. G10L 15/197 (2013.01); G10L 15/04 (2013.01); G10L 15/30 (2013.01); G10L 15/22 (2006.01); G10L 15/08 (2006.01)
CPC G10L 15/197 (2013.01) [G10L 15/04 (2013.01); G10L 15/22 (2013.01); G10L 15/30 (2013.01); G10L 2015/088 (2013.01); G10L 2015/223 (2013.01)] 20 Claims
 
1. A computer-implemented method comprising:
generating, by a computer, a plurality of segments of a plurality of audio signals, including one or more candidate segments of a first audio signal and one or more query segments of a second audio signal;
extracting, by the computer, a plurality of features for each segment of the plurality of segments;
determining, by the computer, for a candidate segment of the one or more candidate segments of the first audio signal a plurality of similarity scores corresponding to the one or more query segments of the second audio signal, each similarity score of the plurality of similarity scores indicating a similarity of the features of the candidate segment with respect to the features of a corresponding query segment of the one or more query segments of the second audio signal;
identifying, by the computer, a discovered keyword included in the candidate segment, in response to determining that at least one similarity score of the plurality of similarity scores of the candidate segment satisfies a pairwise matching threshold; and
updating, by the computer, a voice detection model associated with the plurality of audio signals to nullify a probability of a portion of an audio signal of the plurality of audio signals having the discovered keyword.