中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

6 records (took 0.018 seconds)

    Unified speech representation learning
    3.
    发明授权
    Unified speech representation learning 有权

    公开(公告)号：US11735171B2

    公开(公告)日：2023-08-22

    申请号：US17320496

    申请日：2021-05-14

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

    Inventor： Yao Qian ,  Yu Wu ,  Kenichi Kumatani ,  Shujie Liu ,  Furu Wei ,  Nanshan Zeng ,  Xuedong David Huang ,  Chengyi Wang

    IPC: G10L15/187 ,  G06N20/00 ,  G10L15/06 ,  G10L15/22 ,  G10L15/02

    CPC classification number: G10L15/187 ,  G06N20/00 ,  G10L15/02 ,  G10L15/063 ,  G10L15/22 ,  G10L2015/025

    Abstract: Systems and methods are provided for training a machine learning model to learn speech representations. Labeled speech data or both labeled and unlabeled data sets is applied to a feature extractor of a machine learning model to generate latent speech representations. The latent speech representations are applied to a quantizer to generate quantized latent speech representations and to a transformer context network to generate contextual representations. Each contextual representation included in the contextual representations is aligned with a phoneme label to generate phonetically-aware contextual representations. Quantized latent representations are aligned with phoneme labels to generate phonetically aware latent speech representations. Systems and methods also include randomly replacing a sub-set of the contextual representations with quantized latent speech representations during their alignments to phoneme labels and aligning the phonetically aware latent speech representations to the contextual representations using supervised learning.

    Assertion-based question answering
    4.
    发明授权
    Assertion-based question answering 有权

    公开(公告)号：US11327971B2

    公开(公告)日：2022-05-10

    申请号：US16766088

    申请日：2018-12-06

    Applicant: Microsoft Technology Licensing, LLC

    Inventor： Duyu Tang ,  Nan Duan ,  Ming Zhou ,  Wendi Wang ,  Daxin Jiang ,  Shujie Liu ,  Linjun Shou ,  Ming Gong

    IPC: G06F16/2455 ,  G06F16/248

    Abstract: In embodiments of the present disclosure, there is provided an assertion-based question answering manner. After a question and the related passage are obtained, an assertion answer to the question is determined based on content of the passage, and the assertion answer has a predetermined structure and represents a complete semantic meaning. Then, the assertion answer to the question may be outputted to the user. In the embodiments of the present disclosure, the question and the relevant passage are used as input, and a semi-structured assertion answer is output. The assertion answer according to embodiments of the present disclosure can provide richer semantic content than the traditional short answer, and provide a more concise expression than the traditional long answer, thereby ensuring accuracy of the answer while improving the user experience.

    Canonical training for highly configurable multilingual speech
    5.
    发明授权
    Canonical training for highly configurable multilingual speech 有权

    公开(公告)号：US12249336B2

    公开(公告)日：2025-03-11

    申请号：US18573846

    申请日：2021-06-29

    Applicant: Microsoft Technology Licensing, LLC ,  Jinyu Li ,  Long Zhou ,  Xie Sun ,  Shujie Liu

    Inventor： Jinyu Li ,  Long Zhou ,  Xie Sun ,  Shujie Liu

    IPC: G10L15/32 ,  G10L15/00 ,  G10L15/06 ,  G10L15/30

    Abstract: Embodiments are provided for building a configurable multilingual model. A computing system obtains a plurality of language-specific automatic speech recognition modules and a universal automatic speech recognition module trained on a multi-language training dataset comprising training data corresponding to each of the plurality of different languages. The computing system then compiles the universal automatic speech recognition module with the plurality of language-specific automatic speech recognition modules to generate a configurable multilingual model that is configured to selectively and dynamically utilize a sub-set of the plurality of language-specific automatic speech recognition modules with the universal automatic speech recognition module to process audio content in response to user input identifying one or more target languages associated with the audio content.

    Efficiency adjustable speech recognition system
    6.
    发明授权
    Efficiency adjustable speech recognition system 有权

    公开(公告)号：US11715462B2

    公开(公告)日：2023-08-01

    申请号：US17244891

    申请日：2021-04-29

    Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC

    Inventor： Yu Wu ,  Jinyu Li ,  Shujie Liu ,  Xie Chen ,  Chengyi Wang

    IPC: G10L15/16 ,  G06N3/08 ,  G10L15/06 ,  G10L15/22 ,  G06N3/044

    CPC classification number: G10L15/16 ,  G06N3/044 ,  G06N3/08 ,  G10L15/063 ,  G10L15/22

    Abstract: A computing system is configured to generate a transformer-transducer-based deep neural network. The transformer-transducer-based deep neural network comprises a transformer encoder network and a transducer predictor network. The transformer encoder network has a plurality of layers, each of which includes a multi-head attention network sublayer and a feed-forward network sublayer. The computing system trains an end-to-end (E2E) automatic speech recognition (ASR) model, using the transformer-transducer-based deep neural network. The E2E ASR model has one or more adjustable hyperparameters that are configured to dynamically adjust an efficiency or a performance of E2E ASR model when the E2E ASR model is deployed onto a device or executed by the device.

Patent Agency Ranking