中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

26 records (took 0.018 seconds)

    DYNAMICALLY ADAPTING GIVEN ASSISTANT OUTPUT BASED ON A GIVEN PERSONA ASSIGNED TO AN AUTOMATED ASSISTANT
    1.
    发明公开
    DYNAMICALLY ADAPTING GIVEN ASSISTANT OUTPUT BASED ON A GIVEN PERSONA ASSIGNED TO AN AUTOMATED ASSISTANT 审中-公开

    公开(公告)号：US20230343323A1

    公开(公告)日：2023-10-26

    申请号：US17726244

    申请日：2022-04-21

    Applicant: GOOGLE LLC

    Inventor： Martin Baeuml ,  Thushan Amarasiriwardena ,  Roberto Pieraccini ,  Gianluca Martini

    IPC: G10L13/10 ,  G10L15/22 ,  G10L15/18

    CPC classification number: G10L13/10 ,  G10L15/22 ,  G10L15/1815 ,  G10L2015/223

    Abstract: Implementations relate to dynamically adapting a given assistant output based on a given persona, from among a plurality of disparate personas, assigned to an automated assistant. In some implementations, the given assistant output can be generated and subsequently adapted based on the given persona assigned to the automated assistant. In other implementations, the given assistant output can be generated specific to the given persona and without having to subsequently adapt the given assistant output to the given persona. Notably, the given assistant output can include a stream of textual content to be synthesized for audible presentation to the user, and a stream of visual cues utilized in controlling a display of a client device and/or in controlling a visualized representation of the automated assistant. Various implementations utilize large language models (LLMs), or output previously generated utilizing LLMs, to reflect the given persona in the given assistant output.

    ACOUSTIC MODEL TRAINING USING CORRECTED TERMS
    2.
    发明公开
    ACOUSTIC MODEL TRAINING USING CORRECTED TERMS 审中-公开

    公开(公告)号：US20230274729A1

    公开(公告)日：2023-08-31

    申请号：US18312587

    申请日：2023-05-04

    Applicant: Google LLC

    Inventor： Olga Kapralova ,  Evgeny A. Cherepanov ,  Dmitry Osmakov ,  Martin Baeuml ,  Gleb Skobeltsyn

    IPC: G10L15/06 ,  G10L15/22 ,  G10L15/32 ,  G10L15/01 ,  G10L15/10

    CPC classification number: G10L15/063 ,  G10L15/06 ,  G10L15/22 ,  G10L15/32 ,  G10L15/01 ,  G10L15/10 ,  G10L2015/0635 ,  G10L2015/0638

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving first audio data corresponding to an utterance; obtaining a first transcription of the first audio data; receiving data indicating (i) a selection of one or more terms of the first transcription and (ii) one or more of replacement terms; determining that one or more of the replacement terms are classified as a correction of one or more of the selected terms; in response to determining that the one or more of the replacement terms are classified as a correction of the one or more of the selected terms, obtaining a first portion of the first audio data that corresponds to one or more terms of the first transcription; and using the first portion of the first audio data that is associated with the one or more terms of the first transcription to train an acoustic model for recognizing the one or more of the replacement terms.

    Proactive incorporation of unsolicited content into human-to-computer dialogs
    3.
    发明授权
    Proactive incorporation of unsolicited content into human-to-computer dialogs 有权

    公开(公告)号：US10482882B2

    公开(公告)日：2019-11-19

    申请号：US15825919

    申请日：2017-11-29

    Applicant: Google LLC

    Inventor： Vladimir Vuskovic ,  Stephan Wenger ,  Zineb Ait Bahajji ,  Martin Baeuml ,  Alexandru Dovlecel ,  Gleb Skobeltsyn

    IPC: G10L15/22 ,  G06F17/27 ,  G10L15/18

    Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.

    Proactive incorporation of unsolicited content into human-to-computer dialogs
    4.
    发明授权
    Proactive incorporation of unsolicited content into human-to-computer dialogs 有权

    公开(公告)号：US12183342B2

    公开(公告)日：2024-12-31

    申请号：US18230581

    申请日：2023-08-04

    Applicant: GOOGLE LLC

    Inventor： Vladimir Vuskovic ,  Stephan Wenger ,  Zineb Ait Bahajji ,  Martin Baeuml ,  Alexandru Dovlecel ,  Gleb Skobeltsyn

    IPC: G10L15/22 ,  G06F40/295 ,  G06F40/35 ,  G06F40/56 ,  G10L15/18

    Abstract: Methods, apparatus, and computer readable media are described related to automated assistants that proactively incorporate, into human-to-computer dialog sessions, unsolicited content of potential interest to a user. In various implementations, based on content of an existing human-to-computer dialog session between a user and an automated assistant, an entity mentioned by the user or automated assistant may be identified. Fact(s)s related to the entity or to another entity that is related to the entity may be identified based on entity data contained in database(s). For each of the fact(s), a corresponding measure of potential interest to the user may be determined. Unsolicited natural language content may then be generated that includes one or more of the facts selected based on the corresponding measure(s) of potential interest. The automated assistant may then incorporate the unsolicited content into the existing human-to-computer dialog session or a subsequent human-to-computer dialog session.

    Acoustic model training using corrected terms
    7.
    发明授权
    Acoustic model training using corrected terms 有权

    公开(公告)号：US11682381B2

    公开(公告)日：2023-06-20

    申请号：US17457421

    申请日：2021-12-02

    Applicant: Google LLC

    Inventor： Olga Kapralova ,  Evgeny A. Cherepanov ,  Dmitry Osmakov ,  Martin Baeuml ,  Gleb Skobeltsyn

    IPC: G10L15/06 ,  G10L15/22 ,  G10L15/32 ,  G10L15/01 ,  G10L15/10

    CPC classification number: G10L15/063 ,  G10L15/01 ,  G10L15/06 ,  G10L15/10 ,  G10L15/22 ,  G10L15/32 ,  G10L2015/0635 ,  G10L2015/0638

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving first audio data corresponding to an utterance; obtaining a first transcription of the first audio data; receiving data indicating (i) a selection of one or more terms of the first transcription and (ii) one or more of replacement terms; determining that one or more of the replacement terms are classified as a correction of one or more of the selected terms; in response to determining that the one or more of the replacement terms are classified as a correction of the one or more of the selected terms, obtaining a first portion of the first audio data that corresponds to one or more terms of the first transcription; and using the first portion of the first audio data that is associated with the one or more terms of the first transcription to train an acoustic model for recognizing the one or more of the replacement terms.

    USING LARGE LANGUAGE MODEL(S) IN GENERATING AUTOMATED ASSISTANT RESPONSE(S
    8.
    发明申请
    USING LARGE LANGUAGE MODEL(S) IN GENERATING AUTOMATED ASSISTANT RESPONSE(S 有权

    公开(公告)号：US20230074406A1

    公开(公告)日：2023-03-09

    申请号：US17532794

    申请日：2021-11-22

    Applicant: GOOGLE LLC

    Inventor： Martin Baeuml ,  Thushan Amarasiriwardena ,  Roberto Pieraccini ,  Vikram Sridar ,  Daniel De Freitas Adiwardana ,  Noam M. Shazeer ,  Quoc Le

    IPC: G10L15/183 ,  G10L15/22

    Abstract: As part of a dialog session between a user and an automated assistant, implementations can receive a stream of audio data that captures a spoken utterance including an assistant query, determine, based on processing the stream of audio data, a set of assistant outputs that are each predicted to be responsive to the assistant query, process, using large language model (LLM) output(s), the assistant outputs and context of the dialog session to generate a set of modified assistant outputs, and cause given modified assistant output, from among the set of modified assistant outputs, to be provided for presentation to the user in response to the spoken utterance. In some implementations, the LLM output(s) can be generated in an offline manner for subsequent use in an online manner. In additional or alternative implementations, the LLM output(s) can be generated in an online manner when the spoken utterance is received.

    Acoustic model training using corrected terms
    10.
    发明授权
    Acoustic model training using corrected terms 有权

    公开(公告)号：US11200887B2

    公开(公告)日：2021-12-14

    申请号：US16837393

    申请日：2020-04-01

    Applicant: Google LLC

    Inventor： Olga Kapralova ,  Evgeny A. Cherepanov ,  Dmitry Osmakov ,  Martin Baeuml ,  Gleb Skobeltsyn

    IPC: G10L15/06 ,  G10L15/22 ,  G10L15/32 ,  G10L15/01 ,  G10L15/10

    Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for speech recognition. One of the methods includes receiving first audio data corresponding to an utterance; obtaining a first transcription of the first audio data; receiving data indicating (i) a selection of one or more terms of the first transcription and (ii) one or more of replacement terms; determining that one or more of the replacement terms are classified as a correction of one or more of the selected terms; in response to determining that the one or more of the replacement terms are classified as a correction of the one or more of the selected terms, obtaining a first portion of the first audio data that corresponds to one or more terms of the first transcription; and using the first portion of the first audio data that is associated with the one or more terms of the first transcription to train an acoustic model for recognizing the one or more of the replacement terms.

Patent Agency Ranking