中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

56 records (took 0.019 seconds)

    Training Keyword Spotters
    11.
    发明申请
    Training Keyword Spotters 有权

    公开(公告)号：US20220262345A1

    公开(公告)日：2022-08-18

    申请号：US17662021

    申请日：2022-05-04

    Applicant: Google LLC

    Inventor： Matthew Sharifi ,  Kevin Kilgour ,  Dominik Roblek ,  James Lin

    IPC: G10L15/06 ,  G06N3/04 ,  G06N3/08 ,  G10L13/00 ,  G10L15/16 ,  G10L15/22

    Abstract: A method of training a custom hotword model includes receiving a first set of training audio samples. The method also includes generating, using a speech embedding model configured to receive the first set of training audio samples as input, a corresponding hotword embedding representative of a custom hotword for each training audio sample of the first set of training audio samples. The speech embedding model is pre-trained on a different set of training audio samples with a greater number of training audio samples than the first set of training audio samples The method further includes training the custom hotword model to detect a presence of the custom hotword in audio data. The custom hotword model is configured to receive, as input, each corresponding hotword embedding and to classify, as output, each corresponding hotword embedding as corresponding to the custom hotword.

    Training keyword spotters
    12.
    发明授权
    Training keyword spotters 有权

    公开(公告)号：US11341954B2

    公开(公告)日：2022-05-24

    申请号：US16717518

    申请日：2019-12-17

    Applicant: Google LLC

    Inventor： Matthew Sharifi ,  Kevin Kilgour ,  Dominik Roblek ,  James Lin

    IPC: G10L15/06 ,  G06N3/04 ,  G06N3/08 ,  G10L13/00 ,  G10L15/16 ,  G10L15/22 ,  G10L15/08

    Abstract: A method of training a custom hotword model includes receiving a first set of training audio samples. The method also includes generating, using a speech embedding model configured to receive the first set of training audio samples as input, a corresponding hotword embedding representative of a custom hotword for each training audio sample of the first set of training audio samples. The speech embedding model is pre-trained on a different set of training audio samples with a greater number of training audio samples than the first set of training audio samples. The method further includes training the custom hotword model to detect a presence of the custom hotword in audio data. The custom hotword model is configured to receive, as input, each corresponding hotword embedding and to classify, as output, each corresponding hotword embedding as corresponding to the custom hotword.

    AUDIO PROCESSING WITH NEURAL NETWORKS
    14.
    发明申请
    AUDIO PROCESSING WITH NEURAL NETWORKS 有权

    公开(公告)号：US20210256379A1

    公开(公告)日：2021-08-19

    申请号：US17306934

    申请日：2021-05-03

    Applicant: Google LLC

    Inventor： Dominik Roblek ,  Matthew Sharifi

    IPC: G06N3/08 ,  G06N3/04 ,  G10L25/30 ,  G06F3/16

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for audio processing using neural networks. One of the systems includes multiple neural network layers, wherein the neural network system is configured to receive time domain features of an audio sample and to process the time domain features to generate a neural network output for the audio sample, the plurality of neural network layers comprising: a frequency-transform (F-T) layer that is configured to apply a transformation defined by a set of F-T layer parameters that transforms a window of time domain features into frequency domain features; and one or more other neural network layers having respective layer parameters, wherein the one or more neural network layers are configured to process frequency domain features to generate a neural network output.

    Personalized entity repository
    15.
    发明授权
    Personalized entity repository 有权

    公开(公告)号：US11089457B2

    公开(公告)日：2021-08-10

    申请号：US16241704

    申请日：2019-01-07

    Applicant: Google LLC

    Inventor： Matthew Sharifi ,  Jorge Pereira ,  Dominik Roblek ,  Julian Odell ,  Cong Li ,  David Petrou

    IPC: H04W4/18 ,  H04W4/60 ,  G06F16/248 ,  G06F16/9535 ,  G06F16/2457 ,  H04W4/029 ,  G06F16/907 ,  G06F16/587 ,  G06K9/32 ,  H04L29/08 ,  G06F16/23

    Abstract: Systems and methods are provided for a personalized entity repository. For example, a computing device comprises a personalized entity repository having fixed sets of entities from an entity repository stored at a server, a processor, and memory storing instructions that cause the computing device to identify fixed sets of entities that are relevant to a user based on context associated with the computing device, rank the fixed sets by relevancy, and update the personalized entity repository using selected sets determined based on the rank and on set usage parameters applicable to the user. In another example, a method includes generating fixed sets of entities from an entity repository, including location-based sets and topic-based sets, and providing a subset of the fixed sets to a client, the client requesting the subset based on the client's location and on items identified in content generated for display on the client.

    SEGMENT-BASED SPEAKER VERIFICATION USING DYNAMICALLY GENERATED PHRASES
    18.
    发明申请
    SEGMENT-BASED SPEAKER VERIFICATION USING DYNAMICALLY GENERATED PHRASES 审中-公开

    公开(公告)号：US20200075029A1

    公开(公告)日：2020-03-05

    申请号：US16675420

    申请日：2019-11-06

    Applicant: Google LLC

    Inventor： Dominik Roblek ,  Matthew Sharifi

    IPC: G10L17/24 ,  G10L17/04 ,  G10L15/02

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for verifying an identity of a user. The methods, systems, and apparatus include actions of receiving a request for a verification phrase for verifying an identity of a user. Additional actions include, in response to receiving the request for the verification phrase for verifying the identity of the user, identifying subwords to be included in the verification phrase and in response to identifying the subwords to be included in the verification phrase, obtaining a candidate phrase that includes at least some of the identified subwords as the verification phrase. Further actions include providing the verification phrase as a response to the request for the verification phrase for verifying the identity of the user.

    DYNAMIC DISPLAY OF CONTENT CONSUMPTION BY GEOGRAPHIC LOCATION
    19.
    发明申请
    DYNAMIC DISPLAY OF CONTENT CONSUMPTION BY GEOGRAPHIC LOCATION 审中-公开

    公开(公告)号：US20190220473A1

    公开(公告)日：2019-07-18

    申请号：US16364152

    申请日：2019-03-25

    Applicant: Google LLC

    Inventor： Matthew Sharifi ,  Annie Chen ,  Dominik Roblek

    IPC: G06F16/29 ,  G06F16/9535 ,  G06F16/2457 ,  G06F16/9537 ,  G09B29/00 ,  G06Q10/06

    CPC classification number: G06F16/29 ,  G06F16/24578 ,  G06F16/78 ,  G06F16/9535 ,  G06F16/9537 ,  G06Q10/0637 ,  G09B29/006 ,  G09B29/007

    Abstract: This disclosure relates to a method for providing a display of content consumption by geographic location. The method includes storing, in a data store, geographic locations of a set of users consuming content items and consumption characteristics of the content items, wherein the content items are identified by user devices at the geographic locations while the content items are played by source devices external to the user devices, and wherein information about a content item of the identified content items, which is consumed by a user of the set of users, is transmitted to the server system by a user device of the user. The method also includes extracting, from the data store, geographic locations of consumption and a set of consumption characteristics of each content item of the identified content items, wherein the set of consumption characteristics comprises a title and times of consumption of the content item by the set of users. The method further includes filtering the identified content items based on at least one filter that pertains to times of content consumption by the set of users, ranking the filtered content items based on the geographic locations of consumptions and consumption statistics, selecting, from the ranked content items, popular content items at particular geographic locations of consumption and over a time period, and generating a geographic map displaying to a user each of the selected popular content items at one or more of the particular geographic locations of consumption, the map to display a title and an icon to represent each of the selected popular content items

    Self-supervised audio representation learning for mobile devices
    20.
    发明授权
    Self-supervised audio representation learning for mobile devices 有权

    公开(公告)号：US12165663B2

    公开(公告)日：2024-12-10

    申请号：US17986477

    申请日：2022-11-14

    Applicant: Google LLC

    Inventor： Beat Gfeller ,  Dominik Roblek ,  Félix de Chaumont Quitry ,  Marco Tagliasacchi

    IPC: G10L19/035 ,  G06N20/00 ,  G10L19/038 ,  G10L25/18

    Abstract: Systems and methods for training a machine-learned model are provided. A method can include can include obtaining an unlabeled audio signal, sampling the unlabeled audio signal to select one or more sampled slices, inputting the one or more sampled slices into a machine-learned model, receiving, as an output of the machine-learned model, one or more determined characteristics associated with the audio signal, determining a loss function for the machine-learned model based at least in part on a difference between the one or more determined characteristics and one or more corresponding ground truth characteristics of the audio signal, and training the machine-learned model from end to end based at least in part on the loss function. The one or more determined characteristics can include one or more reconstructed portions of the audio signal temporally adjacent to the one or more sampled slices or an estimated distance between two sampled slices.

Patent Agency Ranking