知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

31 records (took 0.024 seconds)

    Self-supervised audio representation learning for mobile devices
    1.
    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.

    Self-supervised audio representation learning for mobile devices
    3.
    发明授权
    Self-supervised audio representation learning for mobile devices 有权

    公开(公告)号：US11501787B2

    公开(公告)日：2022-11-15

    申请号：US16548146

    申请日：2019-08-22

    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.

    Self-supervised pitch estimation
    7.
    发明授权
    Self-supervised pitch estimation 有权

    公开(公告)号：US11756530B2

    公开(公告)日：2023-09-12

    申请号：US17640579

    申请日：2020-09-25

    Applicant: GOOGLE LLC

    Inventor： Marco Tagliasacchi ,  Mihajlo Velimirovic ,  Matthew Sharifi ,  Dominik Roblek ,  Christian Frank ,  Beat Gfeller

    IPC: G10L15/06 ,  G10L21/013 ,  G10L25/30 ,  G10L25/90

    CPC classification number: G10L15/063 ,  G10L21/013 ,  G10L25/30 ,  G10L25/90

    Abstract: Example embodiments relate to techniques for training artificial neural networks or oilier machine-learning encoders to accurately predict the pitch of input audio samples in a semitone or otherwise logarithmically-scaled pitch space. An example method may include generating, from a sample of audio data, two training samples by applying two different pitch shifts to the sample of audio training data. This can be done by converting the sample of audio data into the frequency domain and then shifting the transformed data. These known shifts are then compared to the predicted pitches generated by applying the two training samples to the encoder. The encoder is then updated based on the comparison, such that the relative pitch output by the encoder is improved with respect to accuracy. One or more audio samples, labeled with absolute pitch values, can then be used to calibrate the relative pitch values generated by the trained encoder.

    Compressing audio waveforms using neural networks and vector quantizers
    8.
    发明授权
    Compressing audio waveforms using neural networks and vector quantizers 有权

    公开(公告)号：US11600282B2

    公开(公告)日：2023-03-07

    申请号：US17856856

    申请日：2022-07-01

    Applicant: Google LLC

    Inventor： Neil Zeghidour ,  Marco Tagliasacchi ,  Dominik Roblek

    IPC: G10L19/038 ,  G10L25/30 ,  G10L19/00 ,  G06N3/08 ,  G06N3/04

    Abstract: Methods, systems and apparatus, including computer programs encoded on computer storage media. One of the methods includes receiving an audio waveform that includes a respective audio sample for each of a plurality of time steps, processing the audio waveform using an encoder neural network to generate a plurality of feature vectors representing the audio waveform, generating a respective coded representation of each of the plurality of feature vectors using a plurality of vector quantizers that are each associated with a respective codebook of code vectors, wherein the respective coded representation of each feature vector identifies a plurality of code vectors, including a respective code vector from the codebook of each vector quantizer, that define a quantized representation of the feature vector, and generating a compressed representation of the audio waveform by compressing the respective coded representation of each of the plurality of feature vectors.

    MULTI-TASK ADAPTER NEURAL NETWORKS
    9.
    发明申请
    MULTI-TASK ADAPTER NEURAL NETWORKS 有权

    公开(公告)号：US20220383112A1

    公开(公告)日：2022-12-01

    申请号：US17764005

    申请日：2020-09-23

    Applicant: Google LLC

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

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

    Abstract: A system including a multi-task adapter neural network for performing multiple machine learning tasks is described. The adapter neural network is configured to receive a shared input for the machine learning tasks, and process the shared input to generate, for each of the machine learning tasks, a respective predicted output. The adapter neural network includes (i) a shared encoder configured to receive the shared input and to process the shared input to extract shared feature representations for the machine learning tasks, and (ii) multiple task-adapter encoders, each of the task-adapter encoders being associated with a respective machine learning task in the machine learning tasks and configured to: receive the shared input, receive the shared feature representations from the shared encoder, and process the shared input and the shared feature representations to generate the respective predicted output for the respective machine learning task.

    Self-Supervised Audio Representation Learning for Mobile Devices
    10.
    发明申请
    Self-Supervised Audio Representation Learning for Mobile Devices 有权

    公开(公告)号：US20210056980A1

    公开(公告)日：2021-02-25

    申请号：US16548146

    申请日：2019-08-22

    Applicant: Google LLC

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

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

    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