中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

40 records (took 0.022 seconds)

    Recurrent neural networks for online sequence generation
    31.
    发明授权
    Recurrent neural networks for online sequence generation 有权

    公开(公告)号：US10656605B1

    公开(公告)日：2020-05-19

    申请号：US16401791

    申请日：2019-05-02

    Applicant: Google LLC

    Inventor： Chung-Cheng Chiu ,  Navdeep Jaitly ,  Ilya Sutskever ,  Yuping Luo

    IPC: G05B13/02 ,  G10L15/16 ,  G06N3/04 ,  G06F40/44

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a target sequence from a source sequence. In one aspect, the system includes a recurrent neural network configured to, at each time step, receive am input for the time step and process the input to generate a progress score and a set of output scores; and a subsystem configured to, at each time step, generate the recurrent neural network input and provide the input to the recurrent neural network; determine, from the progress score, whether or not to emit a new output at the time step; and, in response to determining to emit a new output, select an output using the output scores and emit the selected output as the output at a next position in the output order.

    Cascaded encoders for simplified streaming and non-streaming ASR
    32.
    发明授权
    Cascaded encoders for simplified streaming and non-streaming ASR 有权

    公开(公告)号：US12154581B2

    公开(公告)日：2024-11-26

    申请号：US17237021

    申请日：2021-04-21

    Applicant: Google LLC

    Inventor： Arun Narayanan ,  Tara Sainath ,  Chung-Cheng Chiu ,  Ruoming Pang ,  Rohit Prabhavalkar ,  Jiahui Yu ,  Ehsan Variani ,  Trevor Strohman

    IPC: G10L19/16 ,  G06N3/08 ,  G10L15/00 ,  G10L15/16 ,  G10L15/32 ,  G10L25/30

    Abstract: An automated speech recognition (ASR) model includes a first encoder, a second encoder, and a decoder. The first encoder receives, as input, a sequence of acoustic frames, and generates, at each of a plurality of output steps, a first higher order feature representation for a corresponding acoustic frame in the sequence of acoustic frames. The second encoder receives, as input, the first higher order feature representation generated by the first encoder at each of the plurality of output steps, and generates, at each of the plurality of output steps, a second higher order feature representation for a corresponding first higher order feature frame. The decoder receives, as input, the second higher order feature representation generated by the second encoder at each of the plurality of output steps, and generates, at each of the plurality of time steps, a first probability distribution over possible speech recognition hypotheses.

    Contrastive Learning and Masked Modeling for End-To-End Self-Supervised Pre-Training
    34.
    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.

    Recurrent neural networks for online sequence generation
    37.
    发明授权
    Recurrent neural networks for online sequence generation 有权

    公开(公告)号：US11625572B2

    公开(公告)日：2023-04-11

    申请号：US16610466

    申请日：2018-05-03

    Applicant: GOOGLE LLC

    Inventor： Chung-Cheng Chiu ,  Navdeep Jaitly ,  John Dieterich Lawson ,  George Jay Tucker

    IPC: G06N3/04 ,  G06N3/08

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating a target sequence from a source sequence. In one aspect, the system includes a recurrent neural network configured to, at each time step, receive an input for the time step and process the input to generate a progress score and a set of output scores; and a subsystem configured to, at each time step, generate the recurrent neural network input and provide the input to the recurrent neural network; determine, from the progress score, whether or not to emit a new output at the time step; and, in response to determining to emit a new output, select an output using the output scores and emit the selected output as the output at a next position in the output order.

Patent Agency Ranking