Self-supervised audio representation learning for mobile devices

    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

    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

    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

    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.

    Compressing audio waveforms using neural networks and vector quantizers

    公开(公告)号:US11990148B2

    公开(公告)日:2024-05-21

    申请号:US18106094

    申请日:2023-02-06

    Applicant: Google LLC

    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.

    COMPRESSING AUDIO WAVEFORMS USING NEURAL NETWORKS AND VECTOR QUANTIZERS

    公开(公告)号:US20230019128A1

    公开(公告)日:2023-01-19

    申请号:US17856856

    申请日:2022-07-01

    Applicant: Google LLC

    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.

    Text-Conditioned Speech Inpainting
    10.
    发明申请

    公开(公告)号:US20250149022A1

    公开(公告)日:2025-05-08

    申请号:US18837723

    申请日:2023-02-13

    Applicant: Google LLC

    Abstract: Provided are systems, methods, and machine learning models for filling in gaps (e.g., of up to one second) in speech samples by leveraging an auxiliary textual input. Example machine learning models described herein can perform speech inpainting with the appropriate content, while maintaining speaker identity, prosody and recording environment conditions, and generalizing to unseen speakers. This approach significantly outperforms baselines constructed using adaptive TTS, as judged by human raters in side-by-side preference and MOS tests.

Patent Agency Ranking