中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

69 records (took 0.021 seconds)

    Neural architecture search with factorized hierarchical search space
    65.
    发明授权
    Neural architecture search with factorized hierarchical search space 有权

    公开(公告)号：US11531861B2

    公开(公告)日：2022-12-20

    申请号：US16258927

    申请日：2019-01-28

    Applicant: Google LLC

    Inventor： Mingxing Tan ,  Quoc Le ,  Bo Chen ,  Vijay Vasudevan ,  Ruoming Pang

    IPC: G06N3/04 ,  G06N20/10 ,  G06F17/15 ,  G06N3/08

    Abstract: The present disclosure is directed to an automated neural architecture search approach for designing new neural network architectures such as, for example, resource-constrained mobile CNN models. In particular, the present disclosure provides systems and methods to perform neural architecture search using a novel factorized hierarchical search space that permits layer diversity throughout the network, thereby striking the right balance between flexibility and search space size. The resulting neural architectures are able to be run relatively faster and using relatively fewer computing resources (e.g., less processing power, less memory usage, less power consumption, etc.), all while remaining competitive with or even exceeding the performance (e.g., accuracy) of current state-of-the-art mobile-optimized models.

    Emitting Word Timings with End-to-End Models
    67.
    发明申请
    Emitting Word Timings with End-to-End Models 有权

    公开(公告)号：US20210350794A1

    公开(公告)日：2021-11-11

    申请号：US17204852

    申请日：2021-03-17

    Applicant: Google LLC

    Inventor： Tara N. Sainath ,  Basi Garcia ,  David Rybach ,  Trevor Strohman ,  Ruoming Pang

    IPC: G10L15/06 ,  G10L25/30 ,  G10L25/78

    Abstract: A method includes receiving a training example that includes audio data representing a spoken utterance and a ground truth transcription. For each word in the spoken utterance, the method also includes inserting a placeholder symbol before the respective word identifying a respective ground truth alignment for a beginning and an end of the respective word, determining a beginning word piece and an ending word piece, and generating a first constrained alignment for the beginning word piece and a second constrained alignment for the ending word piece. The first constrained alignment is aligned with the ground truth alignment for the beginning of the respective word and the second constrained alignment is aligned with the ground truth alignment for the ending of the respective word. The method also includes constraining an attention head of a second pass decoder by applying the first and second constrained alignments.

    Deliberation Model-Based Two-Pass End-To-End Speech Recognition
    68.
    发明申请
    Deliberation Model-Based Two-Pass End-To-End Speech Recognition 有权

    公开(公告)号：US20210225369A1

    公开(公告)日：2021-07-22

    申请号：US17149018

    申请日：2021-01-14

    Applicant: Google LLC

    Inventor： Ke Hu ,  Tara N. Sainath ,  Ruoming Pang ,  Rohit Prakash Prabhavalkar

    IPC: G10L15/18 ,  G10L15/06 ,  G06N3/04 ,  G10L15/187 ,  G10L15/16 ,  G10L19/00

    Abstract: A method of performing speech recognition using a two-pass deliberation architecture includes receiving a first-pass hypothesis and an encoded acoustic frame and encoding the first-pass hypothesis at a hypothesis encoder. The first-pass hypothesis is generated by a recurrent neural network (RNN) decoder model for the encoded acoustic frame. The method also includes generating, using a first attention mechanism attending to the encoded acoustic frame, a first context vector, and generating, using a second attention mechanism attending to the encoded first-pass hypothesis, a second context vector. The method also includes decoding the first context vector and the second context vector at a context vector decoder to form a second-pass hypothesis

Patent Agency Ranking