-
公开(公告)号：US11942094B2
公开(公告)日：2024-03-26
申请号：US17211791
申请日：2021-03-24
Applicant: Google LLC
Inventor： Roza Chojnacka , Jason Pelecanos , Quan Wang , Ignacio Lopez Moreno
IPC: G10L17/02 , G06F16/9032 , G10L15/08
CPC classification number: G10L17/02 , G06F16/90332 , G10L2015/088
Abstract: A speaker verification method includes receiving audio data corresponding to an utterance, processing a first portion of the audio data that characterizes a predetermined hotword to generate a text-dependent evaluation vector, and generating one or more text-dependent confidence scores. When one of the text-dependent confidence scores satisfies a threshold, the operations include identifying a speaker of the utterance as a respective enrolled user associated with the text-dependent confidence score that satisfies the threshold and initiating performance of an action without performing speaker verification. When none of the text-dependent confidence scores satisfy the threshold, the operations include processing a second portion of the audio data that characterizes a query to generate a text-independent evaluation vector, generating one or more text-independent confidence scores, and determining whether the identity of the speaker of the utterance includes any of the enrolled users.
-
公开(公告)号：US20220366914A1
公开(公告)日：2022-11-17
申请号：US17302926
申请日：2021-05-16
Applicant: Google LLC
Inventor： Ignacio Lopez Moreno , Quan Wang , Jason Pelecanos , Yiling Huang , Mert Saglam
IPC: G10L17/06 , G10L17/18 , G10L17/04 , G06F16/245 , G06N3/08
Abstract: A speaker verification method includes receiving audio data corresponding to an utterance, processing the audio data to generate a reference attentive d-vector representing voice characteristics of the utterance, the evaluation ad-vector includes ne style classes each including a respective value vector concatenated with a corresponding routing vector. The method also includes generating using a self-attention mechanism, at least one multi-condition attention score that indicates a likelihood that the evaluation ad-vector matches a respective reference ad-vector associated with a respective user. The method also includes identifying the speaker of the utterance as the respective user associated with the respective reference ad-vector based on the multi-condition attention score.
-
公开(公告)号：US20220122614A1
公开(公告)日：2022-04-21
申请号：US17076743
申请日：2020-10-21
Applicant: Google LLC
Inventor： Jason Pelecanos , Pu-sen Chao , Yiling Huang , Quan Wang
Abstract: A method for evaluating a verification model includes receiving a first and a second set of verification results where each verification result indicates whether a primary model or an alternative model verifies an identity of a user as a registered user. The method further includes identifying each verification result in the first and second sets that includes a performance metric. The method also includes determining a first score of the primary model based on a number of the verification results identified in the first set that includes the performance metric and determining a second score of the alternative model based on a number of the verification results identified in the second set that includes the performance metric. The method further includes determining whether a verification capability of the alternative model is better than a verification capability of the primary model based on the first score and the second score.
-
Patent Agency Ranking
公开(公告)号：US20240203400A1
公开(公告)日：2024-06-20
申请号：US18394632
申请日：2023-12-22
Applicant: GOOGLE LLC
Inventor： Ignacio Lopez Moreno , Quan Wang , Jason Pelecanos , Li Wan , Alexander Gruenstein , Hakan Erdogan
CPC classification number: G10L15/063 , G10L15/07 , G10L15/20 , G10L17/04 , G10L17/20 , G10L21/0208 , G10L2015/088
Abstract: Implementations relate to an automated assistant that can bypass invocation phrase detection when an estimation of device-to-device distance satisfies a distance threshold. The estimation of distance can be performed for a set of devices, such as a computerized watch and a cellular phone, and/or any other combination of devices. The devices can communicate ultrasonic signals between each other, and the estimated distance can be determined based on when the ultrasonic signals are sent and/or received by each respective device. When an estimated distance satisfies the distance threshold, the automated assistant can operate as if the user is holding onto their cellular phone while wearing their computerized watch. This scenario can indicate that the user may be intending to hold their device to interact with the automated assistant and, based on this indication, the automated assistant can temporarily bypass invocation phrase detection (e.g., invoke the automated assistant).
-
公开(公告)号：US11854533B2
公开(公告)日：2023-12-26
申请号：US17587424
申请日：2022-01-28
Applicant: GOOGLE LLC
Inventor： Ignacio Lopez Moreno , Quan Wang , Jason Pelecanos , Li Wan , Alexander Gruenstein , Hakan Erdogan
IPC: G10L15/16 , G10L15/06 , G10L15/07 , G10L15/20 , G10L17/04 , G10L17/20 , G10L21/0208 , G10L15/08
CPC classification number: G10L15/063 , G10L15/07 , G10L15/20 , G10L17/04 , G10L17/20 , G10L21/0208 , G10L2015/088
Abstract: Techniques disclosed herein enable training and/or utilizing speaker dependent (SD) speech models which are personalizable to any user of a client device. Various implementations include personalizing a SD speech model for a target user by processing, using the SD speech model, a speaker embedding corresponding to the target user along with an instance of audio data. The SD speech model can be personalized for an additional target user by processing, using the SD speech model, an additional speaker embedding, corresponding to the additional target user, along with another instance of audio data. Additional or alternative implementations include training the SD speech model based on a speaker independent speech model using teacher student learning.
-
公开(公告)号：US20230037085A1
公开(公告)日：2023-02-02
申请号：US17788183
申请日：2021-01-07
Applicant: GOOGLE LLC
Inventor： Fadi Biadsy , Johan Schalkwyk , Jason Pelecanos
Abstract: Implementations disclosed herein are directed to techniques for selectively enabling and/or disabling non-transient storage of one or more instances of assistant interaction data for turn(s) of a dialog between a user and an automated assistant. Implementations are additionally or alternatively directed to techniques for retroactive wiping of non-transiently stored assistant interaction data from previous assistant interaction(s).
-
公开(公告)号：US20220157298A1
公开(公告)日：2022-05-19
申请号：US17587424
申请日：2022-01-28
Applicant: GOOGLE LLC
Inventor： Ignacio Lopez Moreno , Quan Wang , Jason Pelecanos , Li Wan , Alexander Gruenstein , Hakan Erdogan
Abstract: Techniques disclosed herein enable training and/or utilizing speaker dependent (SD) speech models which are personalizable to any user of a client device. Various implementations include personalizing a SD speech model for a target user by processing, using the SD speech model, a speaker embedding corresponding to the target user along with an instance of audio data. The SD speech model can be personalized for an additional target user by processing, using the SD speech model, an additional speaker embedding, corresponding to the additional target user, along with another instance of audio data. Additional or alternative implementations include training the SD speech model based on a speaker independent speech model using teacher student learning.
-
公开(公告)号：US20210312907A1
公开(公告)日：2021-10-07
申请号：US17251163
申请日：2019-12-04
Applicant: GOOGLE LLC
Inventor： Ignacio Lopez Moreno , Quan Wang , Jason Pelecanos , Li Wan , Alexander Gruenstein , Hakan Erdogan
Abstract: Techniques disclosed herein enable training and/or utilizing speaker dependent (SD) speech models which are personalizable to any user of a client device. Various implementations include personalizing a SD speech model for a target user by processing, using the SD speech model, a speaker embedding corresponding to the target user along with an instance of audio data. The SD speech model can be personalized for an additional target user by processing, using the SD speech model, an additional speaker embedding, corresponding to the additional target user, along with another instance of audio data. Additional or alternative implementations include training the SD speech model based on a speaker independent speech model using teacher student learning.
-
-
-
-
-
-
-
Search Results
18
records
(took 0.023 seconds)
