Methods and systems for enhancing the detection of synthetic speech

    公开(公告)号:US12210606B1

    公开(公告)日:2025-01-28

    申请号:US18629085

    申请日:2024-04-08

    Abstract: A method for enhancing detection of synthetic speech is provided that includes the step of receiving, by an electronic device, voice biometric data of a user captured while the user was speaking and analyzing the context in which the received voice biometric data was captured. The context includes environmental and situational factors. Moreover, the method includes the steps of analyzing characteristics of the received voice biometric data for anomalies associated with synthetic speech, generating a risk score based on the results of the analysis, and comparing the risk score against a threshold value. In response to determining the risk score fails to satisfy the threshold score, the method includes a step of determining the captured voice biometric data includes anomalies associated with synthetic speech and initiating an alert protocol.

    METHODS AND SYSTEMS FOR DETERMINING THE AUTHENTICITY OF AN IDENTITY DOCUMENT

    公开(公告)号:US20240144713A1

    公开(公告)日:2024-05-02

    申请号:US17977032

    申请日:2022-10-31

    Inventor: Zorana Markovic

    Abstract: A method for determining authenticity of a document is provided that includes the step of capturing, by an electronic device, an image of a document. The document includes image data of a biometric modality of a user and informational data. Moreover, the method includes the steps of cropping the captured image data to include an image of the document only, removing the informational data from the cropped image, and generating a gray scale image from the cropped image. The gray scale image and the cropped image are a pair of images. Furthermore, the method includes the step of simultaneously processing, by a trained machine learning model (MLM) each image in the pair of images, to determine whether the identity document in the captured image is authentic.

    Methods and systems for enhancing the detection of synthetic voice data

    公开(公告)号:US12131750B1

    公开(公告)日:2024-10-29

    申请号:US18660784

    申请日:2024-05-10

    Abstract: A method for enhancing detection of synthetic voice data is provided that includes converting, by an electronic device, monophonic voice data into stereophonic voice data. The stereophonic voice data includes a first channel signal and a second channel signal. Moreover, the method includes decomposing, by a trained machine learning model, the stereophonic voice data into a mid-signal and a side signal. The method also includes determining artifacts indicative of synthetic generation in the structured and secondary artifacts, calculating, based on the determined artifacts, a probability score reflecting the likelihood the monophonic voice data was synthetically generated, and comparing the probability score against a threshold value. When the probability score satisfies the threshold value, there is a high likelihood that the monophonic voice data includes synthetic artifacts, and an alert is generated indicating the monophonic voice data is potentially fraudulent.

    Methods and systems for enhancing detection of fraudulent data

    公开(公告)号:US12164619B1

    公开(公告)日:2024-12-10

    申请号:US18441823

    申请日:2024-02-14

    Abstract: A method for enhancing detection of fraudulent data is provided that includes the step of analyzing, by an electronic device, voice biometric data captured while the user was speaking to determine whether the captured voice biometric data exhibits anomalies associated with fraudulent voice audio data. Moreover, the method includes the steps of analyzing circumstances under which the voice biometric data was captured, analyzing mannerisms of the user while the voice biometric data was captured, and calculating a risk score based on at least the results of the analyses. Furthermore, the method includes the steps of comparing the risk score against a threshold value, and in response to determining the risk score fails to satisfy the threshold value generating an alert having a risk level corresponding to the risk score.

    Enhanced access control
    8.
    发明授权

    公开(公告)号:US11941933B2

    公开(公告)日:2024-03-26

    申请号:US17307010

    申请日:2021-05-04

    Abstract: A method for enhanced access control is provided that includes the steps of displaying buttons, by an electronic device, where each button corresponds to a different service. Moreover, the method includes receiving, by the electronic device, input regarding a selected service, transmitting at least one credential for the selected service to a computer, and capturing, by a camera in communication with the computer, facial image data of a user. The method also includes determining whether the facial image data was taken of a live person. In response to determining the facial image data was taken of a live person, a verification transaction is conducted based on the at least one credential and facial image data. In response to verifying the identity of the user as true, the user is granted access to the selected service.

    Methods and systems for enhancing user liveness detection

    公开(公告)号:US11810401B1

    公开(公告)日:2023-11-07

    申请号:US18301369

    申请日:2023-04-17

    CPC classification number: G06V40/40 G06V40/53 H04L9/0643 G06V2201/10

    Abstract: A method for enhancing user liveness detection is provided that includes receiving image data of a user that includes items of metadata. Moreover, the method includes comparing each item of metadata associated with the received image data against a corresponding item of metadata associated with record image data of the user, and determining whether each item of metadata associated with the received image data matches the corresponding item of metadata. In response to determining at least one item of metadata associated with the received image data does not match the corresponding item of metadata, the method deems the received image data to be genuine and from a live person. In response to determining all items of metadata associated with the received image match the corresponding item of metadata, the method deems the received image data to be fraudulent and not from a living person.

    METHODS AND SYSTEMS FOR AUTHENTICATING USERS

    公开(公告)号:US20250046317A1

    公开(公告)日:2025-02-06

    申请号:US18365974

    申请日:2023-08-05

    Abstract: A method for authenticating users is provided that includes capturing, by an electronic device, audio data of a pass phrase spoken by a user and obtaining record audio data of the pass phrase spoken by the user. Moreover, the method includes creating a first activation sequence from the captured audio data and a second activation sequence from the record audio data, creating a tensor using the first activation sequence and the second activation sequence, and calculating a first weighted activation sequence and a second weighted activation sequence using the tensor. Furthermore, the method includes calculating an embedding for the first weighted activation sequence and an embedding for the second weighted activation sequence and calculating a similarity score between the calculated embeddings. In response to determining the similarity score satisfies a threshold score, the method includes simultaneously successfully authenticating the user and the pass phrase spoken by the user.

Patent Agency Ranking