利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

12 条记录 (耗时 0.014 秒)

    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：US11501787B2

    公开(公告)日：2022-11-15

    申请号：US16548146

    申请日：2019-08-22

    申请人： Google LLC

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

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

    摘要： 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
    2.
    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

    申请人： GOOGLE LLC

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

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

    CPC分类号： G10L15/063 ,  G10L21/013 ,  G10L25/30 ,  G10L25/90

    摘要： 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.

    Self-Supervised Audio Representation Learning for Mobile Devices
    3.
    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

    申请人： Google LLC

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

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

    摘要： 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.

    Conditioned Separation of Arbitrary Sounds based on Machine Learning Models
    6.
    发明公开
    Conditioned Separation of Arbitrary Sounds based on Machine Learning Models 审中-公开

    公开(公告)号：US20230419989A1

    公开(公告)日：2023-12-28

    申请号：US17808653

    申请日：2022-06-24

    申请人： Google LLC

    发明人： Beat Gfeller ,  Kevin Ian Kilgour ,  Marco Tagliasacchi ,  Aren Jansen ,  Scott Thomas Wisdom ,  Qingqing Huang

    IPC分类号： G10L25/84 ,  G10L15/16 ,  G10L15/06 ,  G06N3/04

    CPC分类号： G10L25/84 ,  G10L15/16 ,  G10L15/063 ,  G06N3/0454

    摘要： Example methods include receiving training data comprising a plurality of audio clips and a plurality of textual descriptions of audio. The methods include generating a shared representation comprising a joint embedding. An audio embedding of a given audio clip is within a threshold distance of a text embedding of a textual description of the given audio clip. The methods include generating, based on the joint embedding, a conditioning vector and training, based on the conditioning vector, a neural network to: receive (i) an input audio waveform, and (ii) an input comprising one or more of an input textual description of a target audio source in the input audio waveform, or an audio sample of the target audio source, separate audio corresponding to the target audio source from the input audio waveform, and output the separated audio corresponding to the target audio source in response to the receiving of the input.

    Self-Supervised Audio Representation Learning for Mobile Devices
    7.
    发明申请
    Self-Supervised Audio Representation Learning for Mobile Devices 有权

    公开(公告)号：US20230085596A1

    公开(公告)日：2023-03-16

    申请号：US17986477

    申请日：2022-11-14

    申请人： Google LLC

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

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

    摘要： 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.