M Borkar - US Patent 10,832,683, 2020 - Google Patents
A system and method for efficient universal background model (UBM) training for speaker recognition, including: receiving an audio input, divisible into a plurality of audio frames …
A Khitrov, K Simonchik - US Patent 10,909,991, 2021 - Google Patents
A computer-implemented method for verifying identity of a speaker is proposed. A low dimensional p-vector based on a speech of the speaker is extracted from the generated high …
M Borkar - US Patent 10,950,243, 2021 - Google Patents
(57) ABSTRACT A system and method for improving T-matrix training for speaker recognition are provided. The method includes receiving an audio input, divisible into a …
SS Kopuri, J Moore, S Srinivasan, A Khare… - US Patent …, 2024 - Google Patents
Techniques for enrolling a user in a system's user recognition functionality without requiring the user speak particular speech are described. The system may determine characteristics …
WC Johnson, K Ispiryan, G Khachatryan - US Patent 11,687,791, 2023 - Google Patents
According to some embodiments of the present disclosure, a device is disclosed. In embodiments, the device stores a computer program comprised of a set of encoded …
WC Johnson, K Ispiryan, G Khachatryan - US Patent 11,687,792, 2023 - Google Patents
A method for executing computer programs in a trusted execution environment of a device is disclosed. The method includes retrieving a genomic differentiation object corresponding to …
Implementations relate to automatic generation of speaker features for each of one or more particular text-dependent speaker verifications (TD-SVs) for a user. Implementations can …