中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

13 records (took 0.016 seconds)

    IDENTIFICATION AND UTILIZATION OF MISRECOGNITIONS IN AUTOMATIC SPEECH RECOGNITION
    1.
    发明申请
    IDENTIFICATION AND UTILIZATION OF MISRECOGNITIONS IN AUTOMATIC SPEECH RECOGNITION 有权

    公开(公告)号：US20220139373A1

    公开(公告)日：2022-05-05

    申请号：US17251284

    申请日：2020-07-08

    Applicant: Google LLC

    Inventor： Ágoston Weisz ,  Ignacio Lopez Moreno ,  Alexandru Dovlecel

    IPC: G10L15/06 ,  G10L15/02 ,  G10L15/22

    Abstract: Techniques are disclosed that enable determining and/or utilizing a misrecognition of a spoken utterance, where the misrecognition is generated using an automatic speech recognition (ASR) model. Various implementations include determining a recognition based on the spoken utterance and a previous utterance spoken prior to the spoken utterance. Additionally or alternatively, implementations include personalizing an ASR engine for a user based on the spoken utterance and the previous utterance spoken prior to the spoken utterance (e.g., based on audio data capturing the previous utterance and a text representation of the spoken utterance).

    Proactive incorporation of unsolicited content into human-to-computer dialogs
    2.
    发明授权
    Proactive incorporation of unsolicited content into human-to-computer dialogs 有权

    公开(公告)号：US11114100B2

    公开(公告)日：2021-09-07

    申请号：US16549403

    申请日：2019-08-23

    Applicant: Google LLC

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

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

    Speech recognition hypothesis generation according to previous occurrences of hypotheses terms and/or contextual data
    5.
    发明授权
    Speech recognition hypothesis generation according to previous occurrences of hypotheses terms and/or contextual data 有权

    公开(公告)号：US11189264B2

    公开(公告)日：2021-11-30

    申请号：US16614241

    申请日：2019-07-17

    Applicant: Google LLC

    Inventor： Ágoston Weisz ,  Alexandru Dovlecel ,  Gleb Skobeltsyn ,  Evgeny Cherepanov ,  Justas Klimavicius ,  Yihui Ma ,  Lukas Lopatovsky

    IPC: G10L15/07 ,  G10L15/183 ,  G10L15/08

    Abstract: Implementations set forth herein relate to speech recognition techniques for handling variations in speech among users (e.g. due to different accents) and processing features of user context in order to expand a number of speech recognition hypotheses when interpreting a spoken utterance from a user. In order to adapt to an accent of the user, terms common to multiple speech recognition hypotheses can be filtered out in order to identify inconsistent terms apparent in a group of hypotheses. Mappings between inconsistent terms can be stored for subsequent users as term correspondence data. In this way, supplemental speech recognition hypotheses can be generated and subject to probability-based scoring for identifying a speech recognition hypothesis that most correlates to a spoken utterance provided by a user. In some implementations, prior to scoring, hypotheses can be supplemented based on contextual data, such as on-screen content and/or application capabilities.

    Proactive incorporation of unsolicited content into human-to-computer dialogs
    6.
    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.

    Identification and utilization of misrecognitions in automatic speech recognition
    7.
    发明授权
    Identification and utilization of misrecognitions in automatic speech recognition 有权

    公开(公告)号：US12165628B2

    公开(公告)日：2024-12-10

    申请号：US17251284

    申请日：2020-07-08

    Applicant: Google LLC

    Inventor： Ágoston Weisz ,  Ignacio Lopez Moreno ,  Alexandru Dovlecel

    IPC: G10L15/06 ,  G10L15/02 ,  G10L15/22

    Abstract: Techniques are disclosed that enable determining and/or utilizing a misrecognition of a spoken utterance, where the misrecognition is generated using an automatic speech recognition (ASR) model. Various implementations include determining a recognition based on the spoken utterance and a previous utterance spoken prior to the spoken utterance. Additionally or alternatively, implementations include personalizing an ASR engine for a user based on the spoken utterance and the previous utterance spoken prior to the spoken utterance (e.g., based on audio data capturing the previous utterance and a text representation of the spoken utterance).

    SPEECH RECOGNITION HYPOTHESIS GENERATION ACCORDING TO PREVIOUS OCCURRENCES OF HYPOTHESES TERMS AND/OR CONTEXTUAL DATA
    10.
    发明申请
    SPEECH RECOGNITION HYPOTHESIS GENERATION ACCORDING TO PREVIOUS OCCURRENCES OF HYPOTHESES TERMS AND/OR CONTEXTUAL DATA 有权

    公开(公告)号：US20220084503A1

    公开(公告)日：2022-03-17

    申请号：US17536938

    申请日：2021-11-29

    Applicant: GOOGLE LLC

    Inventor： Ágoston Weisz ,  Alexandru Dovlecel ,  Gleb Skobeltsyn ,  Evgeny Cherepanov ,  Justas Klimavicius ,  Yihui Ma ,  Lukas Lopatovsky

    IPC: G10L15/07 ,  G10L15/183 ,  G10L15/08

    Abstract: Implementations set forth herein relate to speech recognition techniques for handling variations in speech among users (e.g. due to different accents) and processing features of user context in order to expand a number of speech recognition hypotheses when interpreting a spoken utterance from a user. In order to adapt to an accent of the user, terms common to multiple speech recognition hypotheses can be filtered out in order to identify inconsistent terms apparent in a group of hypotheses. Mappings between inconsistent terms can be stored for subsequent users as term correspondence data. In this way, supplemental speech recognition hypotheses can be generated and subject to probability-based scoring for identifying a speech recognition hypothesis that most correlates to a spoken utterance provided by a user. In some implementations, prior to scoring, hypotheses can be supplemented based on contextual data, such as on-screen content and/or application capabilities.

Patent Agency Ranking