US 9,812,133 B2 | ||
System and method for detecting synthetic speaker verification | ||
Horst J. Schroeter, New Providence, NJ (US) | ||
Assigned to Nuance Communications, Inc., Burlington, MA (US) | ||
Filed by Nuance Communications, Inc., Burlington, MA (US) | ||
Filed on Aug. 5, 2016, as Appl. No. 15/229,376. | ||
Application 15/229,376 is a continuation of application No. 14/859,449, filed on Sep. 21, 2015, granted, now 9,412,382. | ||
Application 14/859,449 is a continuation of application No. 14/454,104, filed on Aug. 7, 2014, granted, now 9,142,218, issued on Sep. 22, 2015. | ||
Application 14/454,104 is a continuation of application No. 13/959,305, filed on Aug. 5, 2013, granted, now 8,805,685, issued on Aug. 12, 2014. | ||
Application 13/959,305 is a continuation of application No. 12/101,482, filed on Apr. 11, 2008, granted, now 8,504,365, issued on Aug. 6, 2013. | ||
Prior Publication US 2016/0343379 A1, Nov. 24, 2016 | ||
This patent is subject to a terminal disclaimer. | ||
Int. Cl. G10L 15/00 (2013.01); G10L 17/24 (2013.01); G10L 17/20 (2013.01); G10L 17/00 (2013.01); G10L 17/04 (2013.01); G10L 17/08 (2013.01) |
CPC G10L 17/24 (2013.01) [G10L 17/005 (2013.01); G10L 17/04 (2013.01); G10L 17/08 (2013.01); G10L 17/20 (2013.01)] | 20 Claims |
1. A method comprising:
receiving, via a processor and from a user, a plurality of speech samples of a same word, wherein the plurality of speech
samples of the same word comprises a current speech sample and a plurality of previously recorded speech samples;
generating, via the processor, a sample similarity from the plurality of speech samples;
making a decision, via the processor, whether to enroll the user in a speech verification system according to a comparison
of the sample similarity with a threshold, wherein the decision is a first decision if the sample similarity is above the
threshold and the decision is a second decision different from and mutually exclusive with the first decision if the sample
similarity is below the threshold; and
enrolling the user in the speech verification system based at least in part on the decision.
|