公开(公告)号：US20220301554A1

公开(公告)日：2022-09-22

申请号：US17833674

申请日：2022-06-06

Applicant: Pindrop Security, Inc.

Inventor： Hrishikesh Rao

IPC: G10L15/197 ,  G10L15/04 ,  G10L15/30 ,  G10L15/22

Abstract: Embodiments described herein provide for a computer that detects one or more keywords of interest using acoustic features, to detect or query commonalities across multiple fraud calls. Embodiments described herein may implement unsupervised keyword spotting (UKWS) or unsupervised word discovery (UWD) in order to identify commonalities across a set of calls, where both UKWS and UWD employ Gaussian Mixture Models (GMM) and one or more dynamic time-warping algorithms. A user may indicate a training exemplar or occurrence of call-specific information, referred to herein as “a named entity,” such as a person's name, an account number, account balance, or order number. The computer may perform a redaction process that computationally nullifies the import of the named entity in the modeling processes described herein.

公开(公告)号：US12190905B2

公开(公告)日：2025-01-07

申请号：US17408281

申请日：2021-08-20

Applicant: PINDROP SECURITY, INC.

Inventor： Hrishikesh Rao ,  Kedar Phatak ,  Elie Khoury

IPC: G10L25/60 ,  G06N20/20 ,  G10L15/02

Abstract: Embodiments described herein provide for a machine-learning architecture for modeling quality measures for enrollment signals. Modeling these enrollment signals enables the machine-learning architecture to identify deviations from expected or ideal enrollment signal in future test phase calls. These differences can be used to generate quality measures for the various audio descriptors or characteristics of audio signals. The quality measures can then be fused at the score-level with the speaker recognition's embedding comparisons for verifying the speaker. Fusing the quality measures with the similarity scoring essentially calibrates the speaker recognition's outputs based on the realities of what is actually expected for the enrolled caller and what was actually observed for the current inbound caller.

公开(公告)号：US20240062753A1

公开(公告)日：2024-02-22

申请号：US18385632

申请日：2023-10-31

Applicant: PINDROP SECURITY, INC.

Inventor： Hrishikesh Rao

IPC: G10L15/197 ,  G10L15/04 ,  G10L15/30 ,  G10L15/22

CPC classification number: G10L15/197 ,  G10L15/04 ,  G10L15/30 ,  G10L15/22 ,  G10L2015/223 ,  G10L2015/088

Abstract: Embodiments described herein provide for a computer that detects one or more keywords of interest using acoustic features, to detect or query commonalities across multiple fraud calls. Embodiments described herein may implement unsupervised keyword spotting (UKWS) or unsupervised word discovery (UWD) in order to identify commonalities across a set of calls, where both UKWS and UWD employ Gaussian Mixture Models (GMM) and one or more dynamic time-warping algorithms. A user may indicate a training exemplar or occurrence of call-specific information, referred to herein as “a named entity,” such as a person's name, an account number, account balance, or order number. The computer may perform a redaction process that computationally nullifies the import of the named entity in the modeling processes described herein.

公开(公告)号：US11810559B2

公开(公告)日：2023-11-07

申请号：US17833674

申请日：2022-06-06

Applicant: Pindrop Security, Inc.

Inventor： Hrishikesh Rao

IPC: G10L15/197 ,  G10L15/04 ,  G10L15/30 ,  G10L15/22 ,  G10L15/08

CPC classification number: G10L15/197 ,  G10L15/04 ,  G10L15/22 ,  G10L15/30 ,  G10L2015/088 ,  G10L2015/223

Abstract: Embodiments described herein provide for a computer that detects one or more keywords of interest using acoustic features, to detect or query commonalities across multiple fraud calls. Embodiments described herein may implement unsupervised keyword spotting (UKWS) or unsupervised word discovery (UWD) in order to identify commonalities across a set of calls, where both UKWS and UWD employ Gaussian Mixture Models (GMM) and one or more dynamic time-warping algorithms. A user may indicate a training exemplar or occurrence of call-specific information, referred to herein as “a named entity,” such as a person's name, an account number, account balance, or order number. The computer may perform a redaction process that computationally nullifies the import of the named entity in the modeling processes described herein.

公开(公告)号：US11355103B2

公开(公告)日：2022-06-07

申请号：US16775149

申请日：2020-01-28

Applicant: PINDROP SECURITY, INC.

Inventor： Hrishikesh Rao

IPC: G10L15/197 ,  G10L15/04 ,  G10L15/30 ,  G10L15/22 ,  G10L15/08

Abstract: Embodiments described herein provide for a computer that detects one or more keywords of interest using acoustic features, to detect or query commonalities across multiple fraud calls. Embodiments described herein may implement unsupervised keyword spotting (UKWS) or unsupervised word discovery (UWD) in order to identify commonalities across a set of calls, where both UKWS and UWD employ Gaussian Mixture Models (GMM) and one or more dynamic time-warping algorithms. A user may indicate a training exemplar or occurrence of call-specific information, referred to herein as “a named entity,” such as a person's name, an account number, account balance, or order number. The computer may perform a redaction process that computationally nullifies the import of the named entity in the modeling processes described herein.