中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

103 records (took 0.027 seconds)

    IMPLICIT BRIDGING OF MACHINE LEARNING TASKS
    62.
    发明申请
    IMPLICIT BRIDGING OF MACHINE LEARNING TASKS 有权

    公开(公告)号：US20250021889A1

    公开(公告)日：2025-01-16

    申请号：US18897967

    申请日：2024-09-26

    Applicant: Google LLC

    Inventor： Zhifeng Chen ,  Michael Schuster ,  Melvin Jose Johnson Premkumar ,  Yonghui Wu ,  Quoc V. Le ,  Maxim Krikun ,  Thorsten Brants

    IPC: G06N20/00 ,  G06F40/44 ,  G06F40/47 ,  G06N3/044 ,  G06N3/045 ,  G06N3/063

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine learning tasks. One method includes receiving (i) a model input, and (ii) data identifying a first machine learning task to be performed on the model input to generate a first type of model output for the model input; augmenting the model input with an identifier for the first machine learning task to generate an augmented model input; and processing the augmented model input using a machine learning model, wherein the machine learning model has been trained on training data to perform a plurality of machine learning tasks including the first machine learning task, and wherein the machine learning model has been configured through training to process the augmented model input to generate a machine learning model output of the first type for the model input.

    Contrastive Learning and Masked Modeling for End-To-End Self-Supervised Pre-Training
    65.
    发明公开
    Contrastive Learning and Masked Modeling for End-To-End Self-Supervised Pre-Training 审中-公开

    公开(公告)号：US20240104352A1

    公开(公告)日：2024-03-28

    申请号：US18012391

    申请日：2022-07-28

    Applicant: Google LLC

    Inventor： Yu Zhang ,  Yu-An Chung ,  Wei Han ,  Chung-Cheng Chiu ,  Weikeng Qin ,  Ruoming Pang ,  Yonghui Wu

    IPC: G06N3/0455

    CPC classification number: G06N3/0455

    Abstract: Provided are improved end-to-end self-supervised pre-training frameworks that leverage a combination of contrastive and masked modeling loss terms. In particular, the present disclosure provides framework that combines contrastive learning and masked modeling, where the former trains the model to discretize input data (e.g., continuous signals such as continuous speech signals) into a finite set of discriminative tokens, and the latter trains the model to learn contextualized representations via solving a masked prediction task consuming the discretized tokens. In contrast to certain existing masked modeling-based pre-training frameworks which rely on an iterative re-clustering and re-training process or other existing frameworks which concatenate two separately trained modules, the proposed framework can enable a model to be optimized in an end-to-end fashion by solving the two self-supervised tasks (the contrastive task and masked modeling) simultaneously.

    END-TO-END SPEECH WAVEFORM GENERATION THROUGH DATA DENSITY GRADIENT ESTIMATION
    70.
    发明公开
    END-TO-END SPEECH WAVEFORM GENERATION THROUGH DATA DENSITY GRADIENT ESTIMATION 审中-公开

    公开(公告)号：US20230252974A1

    公开(公告)日：2023-08-10

    申请号：US18010438

    申请日：2021-09-02

    Applicant: Google LLC

    Inventor： Byungha Chun ,  Mohammad Norouzi ,  Nanxin Chen ,  Ron J. Weiss ,  William Chan ,  Yu Zhang ,  Yonghui Wu

    IPC: G10L13/08 ,  G10L21/0208

    CPC classification number: G10L13/08 ,  G10L21/0208

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating waveforms conditioned on phoneme sequences. In one aspect, a method comprises: obtaining a phoneme sequence; processing the phoneme sequence using an encoder neural network to generate a hidden representation of the phoneme sequence; generating, from the hidden representation, a conditioning input; initializing a current waveform output; and generating a final waveform output that defines an utterance of the phoneme sequence by a speaker by updating the current waveform output at each of a plurality of iterations, wherein each iteration corresponds to a respective noise level, and wherein the updating comprises, at each iteration: processing (i) the current waveform output and (ii) the conditioning input using a noise estimation neural network to generate a noise output; and updating the current waveform output using the noise output and the noise level for the iteration.

Patent Agency Ranking