US 12,323,553 B2
Systems and methods for detecting call provenance from call audio
Vijay Balasubramaniyan, Atlanta, GA (US); Mustaque Ahamad, Atlanta, GA (US); Patrick Gerald Traynor, Decatur, GA (US); Michael Thomas Hunter, Atlanta, GA (US); and Aamir Poonawalla, Atlanta, GA (US)
Assigned to Georgia Tech Research Corporation, Atlanta, GA (US)
Filed by GEORGIA TECH RESEARCH CORPORATION, Atlanta, GA (US)
Filed on Feb. 8, 2024, as Appl. No. 18/436,668.
Application 18/436,668 is a continuation of application No. 18/541,182, filed on Dec. 15, 2023.
Application 18/541,182 is a continuation of application No. 17/338,523, filed on Jun. 3, 2021, granted, now 11,849,065, issued on Dec. 19, 2023.
Application 17/338,523 is a continuation of application No. 16/730,666, filed on Dec. 30, 2019, granted, now 11,050,876, issued on Jun. 29, 2021.
Application 16/730,666 is a continuation of application No. 15/347,440, filed on Nov. 9, 2016, granted, now 10,523,809, issued on Dec. 31, 2019.
Application 15/347,440 is a continuation of application No. 14/715,549, filed on May 18, 2015, granted, now 9,516,497, issued on Dec. 6, 2016.
Application 14/715,549 is a continuation of application No. 13/807,837, granted, now 9,037,113, issued on Apr. 29, 2015, previously published as PCT/US2011/042410, filed on Jun. 29, 2011.
Claims priority of provisional application 61/359,586, filed on Jun. 29, 2010.
Prior Publication US 2024/0223697 A1, Jul. 4, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H04W 24/08 (2009.01); H04L 43/0829 (2022.01); H04L 65/1076 (2022.01); H04M 1/68 (2006.01); H04M 3/22 (2006.01); H04W 12/02 (2009.01); H04M 7/00 (2006.01); H04W 12/12 (2021.01); H04W 12/63 (2021.01); H04W 12/65 (2021.01)
CPC H04M 3/2281 (2013.01) [H04L 43/0829 (2013.01); H04L 65/1076 (2013.01); H04M 1/68 (2013.01); H04W 12/02 (2013.01); H04W 24/08 (2013.01); H04M 7/0078 (2013.01); H04M 2203/558 (2013.01); H04M 2203/6027 (2013.01); H04M 2203/6045 (2013.01); H04W 12/12 (2013.01); H04W 12/63 (2021.01); H04W 12/65 (2021.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
obtaining, by a computer, call data for a call originated at a calling device of a caller, the call data including audio data and indicating one or more characteristics associated with the calling device;
extracting, by the computer, a feature vector using the one or more characteristics associated with the calling device from the call data, the one or more characteristics including at least one of a network or a location associated with the calling device;
generating, by the computer, a risk score associated with the call based upon comparing the feature vector for the one or more characteristics associated with the calling device extracted for the call data against a stored feature vector for one or more stored characteristics stored in one or more databases using a machine learning model trained to generate the risk score based upon training feature vectors from training call data.