Neural translator
    1.
    发明授权

    公开(公告)号:US10162818B2

    公开(公告)日:2018-12-25

    申请号:US15587121

    申请日:2017-05-04

    摘要: A method and apparatus are provided for processing a set of communicated signals associated with a set of muscles, such as the muscles near the larynx of the person, or any other muscles the person use to achieve a desired response. The method includes the steps of attaching a single integrated sensor, for example, near the throat of the person proximate to the larynx and detecting an electrical signal through the sensor. The method further includes the steps of extracting features from the detected electrical signal and continuously transforming them into speech sounds without the need for further modulation. The method also includes comparing the extracted features to a set of prototype features and selecting a prototype feature of the set of prototype features providing a smallest relative difference.

    Neural translator
    2.
    发明授权
    Neural translator 有权
    神经翻译

    公开(公告)号:US08949129B2

    公开(公告)日:2015-02-03

    申请号:US13964715

    申请日:2013-08-12

    摘要: A method and apparatus are provided for processing a set of communicated signals associated with a set of muscles, such as the muscles near the larynx of the person, or any other muscles the person use to achieve a desired response. The method includes the steps of attaching a single integrated sensor, for example, near the throat of the person proximate to the larynx and detecting an electrical signal through the sensor. The method further includes the steps of extracting features from the detected electrical signal and continuously transforming them into speech sounds without the need for further modulation. The method also includes comparing the extracted features to a set of prototype features and selecting a prototype feature of the set of prototype features providing a smallest relative difference.

    摘要翻译: 提供了一种方法和装置,用于处理与一组肌肉相关联的一组传播信号,例如人的喉部附近的肌肉,或者人们用于实现期望的反应的任何其他肌肉。 该方法包括以下步骤:附接单个集成传感器,例如靠近喉部的人的喉部,并通过传感器检测电信号。 该方法还包括以下步骤:从检测到的电信号中提取特征,并将其连续地变换成语音,而不需要进一步调制。 该方法还包括将所提取的特征与一组原型特征进行比较,并且选择提供最小相对差异的原始特征集的原型特征。

    NEURAL TRANSLATOR
    3.
    发明申请

    公开(公告)号:US20220366148A1

    公开(公告)日:2022-11-17

    申请号:US17557720

    申请日:2021-12-21

    摘要: A method and apparatus are provided for processing a set of communicated signals associated with a set of muscles, such as the muscles near the larynx of the person, or any other muscles the person use to achieve a desired response. The method includes the steps of attaching a single integrated sensor, for example, near the throat of the person proximate to the larynx and detecting an electrical signal through the sensor. The method further includes the steps of extracting features from the detected electrical signal and continuously transforming them into speech sounds without the need for further modulation. The method also includes comparing the extracted features to a set of prototype features and selecting a prototype feature of the set of prototype features providing a smallest relative difference.

    NEURAL TRANSLATOR
    4.
    发明申请
    NEURAL TRANSLATOR 审中-公开

    公开(公告)号:US20190121858A1

    公开(公告)日:2019-04-25

    申请号:US16224009

    申请日:2018-12-18

    摘要: A method and apparatus are provided for processing a set of communicated signals associated with a set of muscles, such as the muscles near the larynx of the person, or any other muscles the person use to achieve a desired response. The method includes the steps of attaching a single integrated sensor, for example, near the throat of the person proximate to the larynx and detecting an electrical signal through the sensor. The method further includes the steps of extracting features from the detected electrical signal and continuously transforming them into speech sounds without the need for further modulation. The method also includes comparing the extracted features to a set of prototype features and selecting a prototype feature of the set of prototype features providing a smallest relative difference.

    NEURAL TRANSLATOR
    5.
    发明申请
    NEURAL TRANSLATOR 审中-公开
    神经翻译

    公开(公告)号:US20150213003A1

    公开(公告)日:2015-07-30

    申请号:US14611696

    申请日:2015-02-02

    IPC分类号: G06F17/28

    摘要: A method and apparatus for processing a set of communicated signals associated with a set of muscles, such as the muscles near the larynx of the person, or any other muscles the person use to achieve a desired response. The method may include attaching a sensor near an area of a user's body associated with speech production, detecting an electrical signal from the user's nervous system through the sensor, and processing the detected electrical signal to provide communication capability for the user. The processing may include extracting a set of features of the detected electrical signal. The extracted set of features may be compared with a set of prototype features. The set of prototype features may correspond to at least one of multiple response classes. The multiple response classes may include an affirmative response class and a negative response class.

    摘要翻译: 一种用于处理与一组肌肉相关联的一组传播信号的方法和装置,例如人的喉部附近的肌肉或者人们用于实现期望的反应的任何其他肌肉。 该方法可以包括在与语音产生相关联的用户身体的区域附近附接传感器,通过传感器检测来自用户的神经系统的电信号,以及处理检测到的电信号以为用户提供通信能力。 处理可以包括提取检测到的电信号的一组特征。 提取的特征集合可以与一组原型特征进行比较。 原始特征的集合可以对应于多个响应类别中的至少一个。 多个响应类可以包括肯定响应类和否定响应类。

    NEURAL TRANSLATOR
    6.
    发明申请
    NEURAL TRANSLATOR 有权
    神经翻译

    公开(公告)号:US20130332173A1

    公开(公告)日:2013-12-12

    申请号:US13964715

    申请日:2013-08-12

    IPC分类号: G10L25/48

    摘要: A method and apparatus are provided for processing a set of communicated signals associated with a set of muscles, such as the muscles near the larynx of the person, or any other muscles the person use to achieve a desired response. The method includes the steps of attaching a single integrated sensor, for example, near the throat of the person proximate to the larynx and detecting an electrical signal through the sensor. The method further includes the steps of extracting features from the detected electrical signal and continuously transforming them into speech sounds without the need for further modulation. The method also includes comparing the extracted features to a set of prototype features and selecting a prototype feature of the set of prototype features providing a smallest relative difference.

    摘要翻译: 提供了一种方法和装置,用于处理与一组肌肉相关联的一组传播信号,例如人的喉部附近的肌肉,或者人们用于实现期望的反应的任何其他肌肉。 该方法包括以下步骤:附接单个集成传感器,例如靠近喉部的人的喉部,并通过传感器检测电信号。 该方法还包括以下步骤:从检测到的电信号中提取特征,并将其连续变换成语音,而不需要进一步的调制。 该方法还包括将所提取的特征与一组原型特征进行比较,并且选择提供最小相对差异的原始特征集的原型特征。

    Neural translator
    7.
    发明申请
    Neural translator 有权
    神经翻译

    公开(公告)号:US20080010071A1

    公开(公告)日:2008-01-10

    申请号:US11825785

    申请日:2007-07-09

    IPC分类号: G10L21/00

    摘要: A method and apparatus are provided for processing a set of communicated signals associated with a set of muscles, such as the muscles near the larynx of the person, or any other muscles the person use to achieve a desired response. The method includes the steps of attaching a single integrated sensor, for example, near the throat of the person proximate to the larynx and detecting an electrical signal through the sensor. The method further includes the steps of extracting features from the detected electrical signal and continuously transforming them into speech sounds without the need for further modulation. The method also includes comparing the extracted features to a set of prototype features and selecting a prototype feature of the set of prototype features providing a smallest relative difference.

    摘要翻译: 提供了一种方法和装置,用于处理与一组肌肉相关联的一组传播信号,例如人的喉部附近的肌肉,或者人们用于实现期望的反应的任何其他肌肉。 该方法包括以下步骤:附接单个集成传感器,例如靠近喉部的人的喉部,并通过传感器检测电信号。 该方法还包括以下步骤:从检测到的电信号中提取特征,并将其连续变换成语音,而不需要进一步的调制。 该方法还包括将所提取的特征与一组原型特征进行比较,并且选择提供最小相对差异的原始特征集的原型特征。

    Neural translator
    8.
    发明授权

    公开(公告)号:US08529473B2

    公开(公告)日:2013-09-10

    申请号:US13560675

    申请日:2012-07-27

    IPC分类号: A61B7/00

    摘要: A method and apparatus are provided for processing a set of communicated signals associated with a set of muscles, such as the muscles near the larynx of the person, or any other muscles the person use to achieve a desired response. The method includes the steps of attaching a single integrated sensor, for example, near the throat of the person proximate to the larynx and detecting an electrical signal through the sensor. The method further includes the steps of extracting features from the detected electrical signal and continuously transforming them into speech sounds without the need for further modulation. The method also includes comparing the extracted features to a set of prototype features and selecting a prototype feature of the set of prototype features providing a smallest relative difference.

    Neural translator
    9.
    发明授权

    公开(公告)号:US11205054B2

    公开(公告)日:2021-12-21

    申请号:US16224009

    申请日:2018-12-18

    摘要: A method and apparatus are provided for processing a set of communicated signals associated with a set of muscles, such as the muscles near the larynx of the person, or any other muscles the person use to achieve a desired response. The method includes the steps of attaching a single integrated sensor, for example, near the throat of the person proximate to the larynx and detecting an electrical signal through the sensor. The method further includes the steps of extracting features from the detected electrical signal and continuously transforming them into speech sounds without the need for further modulation. The method also includes comparing the extracted features to a set of prototype features and selecting a prototype feature of the set of prototype features providing a smallest relative difference.

    Neural translator
    10.
    发明授权

    公开(公告)号:US09772997B2

    公开(公告)日:2017-09-26

    申请号:US14611696

    申请日:2015-02-02

    摘要: A method and apparatus for processing a set of communicated signals associated with a set of muscles, such as the muscles near the larynx of the person, or any other muscles the person use to achieve a desired response. The method may include attaching a sensor near an area of a user's body associated with speech production, detecting an electrical signal from the user's nervous system through the sensor, and processing the detected electrical signal to provide communication capability for the user. The processing may include extracting a set of features of the detected electrical signal. The extracted set of features may be compared with a set of prototype features. The set of prototype features may correspond to at least one of multiple response classes. The multiple response classes may include an affirmative response class and a negative response class.