公开(公告)号：US12015637B2

公开(公告)日：2024-06-18

申请号：US16841473

申请日：2020-04-06

Applicant: PINDROP SECURITY, INC.

Inventor： Khaled Lakhdhar ,  Parav Nagarsheth ,  Tianxiang Chen ,  Elie Khoury

IPC: H04L9/40 ,  G06F17/18 ,  G06N3/045 ,  G06N3/084 ,  G06N20/10 ,  G10L17/00 ,  G10L17/04 ,  G10L17/26 ,  G10L19/26 ,  H04L65/75

CPC classification number: H04L63/1466 ,  G06F17/18 ,  G06N3/045 ,  G06N3/084 ,  G06N20/10 ,  G10L17/00 ,  G10L17/04 ,  G10L17/26 ,  G10L19/26 ,  H04L65/75

Abstract: Embodiments described herein provide for automatically detecting whether an audio signal is a spoofed audio signal or a genuine audio signal. A spoof detection system can include an audio signal transforming front end and a classification back end. Both the front end and the back end can include neural networks that can be trained using the same set of labeled audio signals. The audio signal transforming front end can include a one or more neural networks for per-channel energy normalization transformation of the audio signal, and the back end can include a convolution neural network for classification into spoofed or genuine audio signal. In some embodiments, the transforming audio signal front end can include one or more neural networks for bandpass filtering of the audio signals, and the back end can include a residual neural network for audio signal classification into spoofed or genuine audio signal.

公开(公告)号：US11862177B2

公开(公告)日：2024-01-02

申请号：US17155851

申请日：2021-01-22

Applicant: PINDROP SECURITY, INC.

Inventor： Tianxiang Chen ,  Elie Khoury

IPC: G10L17/18 ,  G10L17/02 ,  G10L17/22 ,  G10L17/04 ,  G10L17/08

CPC classification number: G10L17/18 ,  G10L17/02 ,  G10L17/04 ,  G10L17/08 ,  G10L17/22

Abstract: Embodiments described herein provide for systems and methods for implementing a neural network architecture for spoof detection in audio signals. The neural network architecture contains a layers defining embedding extractors that extract embeddings from input audio signals. Spoofprint embeddings are generated for particular system enrollees to detect attempts to spoof the enrollee's voice. Optionally, voiceprint embeddings are generated for the system enrollees to recognize the enrollee's voice. The voiceprints are extracted using features related to the enrollee's voice. The spoofprints are extracted using features related to features of how the enrollee speaks and other artifacts. The spoofprints facilitate detection of efforts to fool voice biometrics using synthesized speech (e.g., deepfakes) that spoof and emulate the enrollee's voice.

公开(公告)号：US11657823B2

公开(公告)日：2023-05-23

申请号：US17107496

申请日：2020-11-30

Applicant: PINDROP SECURITY, INC.

Inventor： Elie Khoury ,  Matthew Garland

IPC: G10L17/20 ,  G10L17/02 ,  G10L17/04 ,  G10L17/18 ,  G10L19/028

CPC classification number: G10L17/20 ,  G10L17/02 ,  G10L17/04 ,  G10L17/18 ,  G10L19/028

Abstract: A system for generating channel-compensated features of a speech signal includes a channel noise simulator that degrades the speech signal, a feed forward convolutional neural network (CNN) that generates channel-compensated features of the degraded speech signal, and a loss function that computes a difference between the channel-compensated features and handcrafted features for the same raw speech signal. Each loss result may be used to update connection weights of the CNN until a predetermined threshold loss is satisfied, and the CNN may be used as a front-end for a deep neural network (DNN) for speaker recognition/verification. The DNN may include convolutional layers, a bottleneck features layer, multiple fully-connected layers and an output layer. The bottleneck features may be used to update connection weights of the convolutional layers, and dropout may be applied to the convolutional layers.

公开(公告)号：US11335353B2

公开(公告)日：2022-05-17

申请号：US16889337

申请日：2020-06-01

Applicant: PINDROP SECURITY, INC.

Inventor： Elie Khoury ,  Matthew Garland

IPC: G10L17/26 ,  H04L29/06 ,  G06F21/32 ,  G06K9/62 ,  G10L25/30 ,  G10L17/18 ,  G10L17/04 ,  G10L15/26 ,  G06V40/10 ,  G06V40/16 ,  G06V40/50

Abstract: A score indicating a likelihood that a first subject is the same as a second subject may be calibrated to compensate for aging of the first subject between samples of age-sensitive biometric characteristics. Age of the first subject obtained at a first sample time and age of the second subject obtained at a second sample time may be averaged, and an age approximation may be generated based on at least the age average and an interval between the first and second samples. The age approximation, the interval between the first and second sample times, and an obtained gender of the subject are used to calibrate the likelihood score.

公开(公告)号：US10692502B2

公开(公告)日：2020-06-23

申请号：US15910387

申请日：2018-03-02

Applicant: PINDROP SECURITY, INC.

Inventor： Elie Khoury ,  Parav Nagarsheth ,  Kailash Patil ,  Matthew Garland

IPC: G10L17/02 ,  G10L17/04 ,  G10L17/06 ,  G10L17/18 ,  G10L19/02 ,  G10L25/24 ,  G10L17/00

Abstract: An automated speaker verification (ASV) system incorporates a first deep neural network to extract deep acoustic features, such as deep CQCC features, from a received voice sample. The deep acoustic features are processed by a second deep neural network that classifies the deep acoustic features according to a determined likelihood of including a spoofing condition. A binary classifier then classifies the voice sample as being genuine or spoofed.

公开(公告)号：US20190385630A1

公开(公告)日：2019-12-19

申请号：US16442279

申请日：2019-06-14

Applicant: PINDROP SECURITY, INC.

Inventor： Ganesh Sivaraman ,  Elie Khoury

IPC: G10L21/0232 ,  G10L25/30 ,  G06N3/04

Abstract: A computer may segment a noisy audio signal into audio frames and execute a deep neural network (DNN) to estimate an instantaneous function of clean speech spectrum and noisy audio spectrum in the audio frame. This instantaneous function may correspond to a ratio of an a-priori signal to noise ratio (SNR) and an a-posteriori SNR of the audio frame. The computer may add estimated instantaneous function to the original noisy audio frame to output an enhanced speech audio frame.

公开(公告)号：US10347256B2

公开(公告)日：2019-07-09

申请号：US15709024

申请日：2017-09-19

Applicant: PINDROP SECURITY, INC.

Inventor： Elie Khoury ,  Matthew Garland

IPC: G10L17/18 ,  G10L17/04 ,  G10L17/20 ,  G10L17/02 ,  G10L19/028

Abstract: A system for generating channel-compensated features of a speech signal includes a channel noise simulator that degrades the speech signal, a feed forward convolutional neural network (CNN) that generates channel-compensated features of the degraded speech signal, and a loss function that computes a difference between the channel-compensated features and handcrafted features for the same raw speech signal. Each loss result may be used to update connection weights of the CNN until a predetermined threshold loss is satisfied, and the CNN may be used as a front-end for a deep neural network (DNN) for speaker recognition/verification. The DNN may include convolutional layers, a bottleneck features layer, multiple fully-connected layers and an output layer. The bottleneck features may be used to update connection weights of the convolutional layers, and dropout may be applied to the convolutional layers.

公开(公告)号：US12266368B2

公开(公告)日：2025-04-01

申请号：US17165180

申请日：2021-02-02

Applicant: PINDROP SECURITY, INC.

Inventor： Ganesh Sivaraman ,  Elie Khoury ,  Avrosh Kumar

IPC: G10L17/04 ,  G06N3/04 ,  G10L17/18

Abstract: Embodiments described herein provide for systems and methods for voice-based cross-channel enrollment and authentication. The systems control for and mitigate against variations in audio signals received across any number of communications channels by training and employing a neural network architecture comprising a speaker verification neural network and a bandwidth expansion neural network. The bandwidth expansion neural network is trained on narrowband audio signals to produce and generate estimated wideband audio signals corresponding to the narrowband audio signals. These estimated wideband audio signals may be fed into one or more downstream applications, such as the speaker verification neural network or embedding extraction neural network. The speaker verification neural network can then compare and score inbound embeddings for a current call against enrolled embeddings, regardless of the channel used to receive the inbound signal or enrollment signal.

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：US11948553B2

公开(公告)日：2024-04-02

申请号：US17192464

申请日：2021-03-04

Applicant: PINDROP SECURITY, INC.

Inventor： Kedar Phatak ,  Elie Khoury

IPC: G10L15/06 ,  G06N3/045 ,  G06N20/00 ,  G10L15/16 ,  G10L25/27

CPC classification number: G10L15/063 ,  G06N3/045 ,  G06N20/00 ,  G10L15/16 ,  G10L25/27

Abstract: Embodiments described herein provide for audio processing operations that evaluate characteristics of audio signals that are independent of the speaker's voice. A neural network architecture trains and applies discriminatory neural networks tasked with modeling and classifying speaker-independent characteristics. The task-specific models generate or extract feature vectors from input audio data based on the trained embedding extraction models. The embeddings from the task-specific models are concatenated to form a deep-phoneprint vector for the input audio signal. The DP vector is a low dimensional representation of the each of the speaker-independent characteristics of the audio signal and applied in various downstream operations.