中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

28 records (took 0.019 seconds)

    MULTI-LAYERED SPEECH RECOGNITION APPARATUS AND METHOD
    2.
    发明申请
    MULTI-LAYERED SPEECH RECOGNITION APPARATUS AND METHOD 有权
    多层语音识别装置及方法

    公开(公告)号：US20120232893A1

    公开(公告)日：2012-09-13

    申请号：US13478656

    申请日：2012-05-23

    Applicant: Jaewon Lee ,  Jeongmi Cho

    Inventor： Jaewon Lee ,  Jeongmi Cho

    IPC: G10L15/00

    CPC classification number: G10L15/08 ,  G10L15/30 ,  G10L15/32

    Abstract: A multi-layered speech recognition apparatus and method, the apparatus includes a client checking whether the client recognizes the speech using a characteristic of speech to be recognized and recognizing the speech or transmitting the characteristic of the speech according to a checked result; and first through N-th servers, wherein the first server checks whether the first server recognizes the speech using the characteristic of the speech transmitted from the client, and recognizes the speech or transmits the characteristic according to a checked result, and wherein an n-th (2≦n≦N) server checks whether the n-th server recognizes the speech using the characteristic of the speech transmitted from an (n−1)-th server, and recognizes the speech or transmits the characteristic according to a checked result.

    Abstract translation: 一种多层语音识别装置和方法，所述装置包括：客户端，根据检查结果，使用要识别的语音特征识别语音，识别语音，或者发送语音的特征; 以及第一至第N服务器，其中第一服务器使用从客户端发送的语音的特征来检查第一服务器是否识别语音，并且根据检查结果识别语音或发送特性，并且其中， （2＆nlE; n＆nlE; N）服务器检查第n个服务器是否使用从第（n-1）个服务器发送的语音的特征识别语音，并且根据检查结果识别语音或发送特性 。

    Speech processing apparatus, medium, and method recognizing and responding to speech using entity information
    3.
    发明授权
    Speech processing apparatus, medium, and method recognizing and responding to speech using entity information 有权
    语音处理装置，媒体和方法，使用实体信息识别和响应语音

    公开(公告)号：US08185397B2

    公开(公告)日：2012-05-22

    申请号：US11377207

    申请日：2006-03-17

    Applicant: Jaewon Lee ,  Inho Kang ,  Haechang Rim ,  Jeongsu Kim

    Inventor： Jaewon Lee ,  Inho Kang ,  Haechang Rim ,  Jeongsu Kim

    IPC: G06F17/27 ,  G10L15/06 ,  G10L21/00

    CPC classification number: G10L15/1815

    Abstract: A speech processing apparatus, medium, and method recognizing speech and responding to the speech. The speech processing apparatus may includes an entity extracting unit which extracts entity information and an upper entity corresponding to the entity information from input speech, a focus determination unit which determines a focus using the extracted entity information requiring a response, a mapping unit which maps lower entity corresponding to the focus with the extracted entity information, and a recognition unit which recognizes a result of arranging the extracted entity information according to semantic association among the lower entities as the input speech. Thus, the speech processing apparatus can accurately recognize grammatically correct speech as well as grammatically incorrect speech and then respond to the speech.

    Abstract translation: 一种语音处理装置，媒体和方法，用于识别语音并响应语音。 语音处理装置可以包括：实体提取单元，其从输入语音中提取实体信息和与实体信息对应的上层实体;焦点确定单元，其使用提取的需要响应的实体信息来确定焦点;映射单元， 与提取的实体信息对应的实体的实体，以及识别单元，其根据下层实体之间的语义关联识别提取的实体信息的排列结果作为输入语音。 因此，语音处理装置可以准确地识别语法正确的语音以及语法上不正确的语音，然后对语音进行响应。

    Multi-layered speech recognition apparatus and method
    4.
    发明申请
    Multi-layered speech recognition apparatus and method 有权
    多层语音识别装置及方法

    公开(公告)号：US20060080105A1

    公开(公告)日：2006-04-13

    申请号：US11120983

    申请日：2005-05-04

    Applicant: Jaewon Lee ,  Jeongmi Cho ,  Kwangil Hwang ,  Yongbeom Lee ,  Jeongsu Kim

    Inventor： Jaewon Lee ,  Jeongmi Cho ,  Kwangil Hwang ,  Yongbeom Lee ,  Jeongsu Kim

    IPC: G10L21/00

    CPC classification number: G10L15/08 ,  G10L15/30 ,  G10L15/32

    Abstract: A multi-layered speech recognition apparatus and method, the apparatus includes a client checking whether the client recognizes the speech using a characteristic of speech to be recognized and recognizing the speech or transmitting the characteristic of the speech according to a checked result; and first through N-th servers, wherein the first server checks whether the first server recognizes the speech using the characteristic of the speech transmitted from the client, and recognizes the speech or transmits the characteristic according to a checked result, and wherein an n-th (2≦n≦N) server checks whether the n-th server recognizes the speech using the characteristic of the speech transmitted from an (n−1)-th server, and recognizes the speech or transmits the characteristic according to a checked result.

    Abstract translation: 一种多层语音识别装置和方法，所述装置包括：客户端，根据检查结果，使用要识别的语音特征识别语音，识别语音，或者发送语音的特征; 以及第一至第N服务器，其中第一服务器使用从客户端发送的语音的特征来检查第一服务器是否识别语音，并且根据检查结果识别语音或发送特性，并且其中， 服务器检查第n个服务器是否使用从第（n-1）个服务器发送的语音的特征识别语音，并且识别语音或者根据 检查结果。

    Puzzle cube and a method for making same
    5.
    发明授权
    Puzzle cube and a method for making same 有权

    公开(公告)号：US10583351B2

    公开(公告)日：2020-03-10

    申请号：US16167148

    申请日：2018-10-22

    Applicant: Jerich Jaewon Lee

    Inventor： Jerich Jaewon Lee

    IPC: A63F9/08

    Abstract: A puzzle cube and a method for making same are provided. In some embodiments, a puzzle cube is provided, the puzzle cube comprising: a central core assembly including a center cross member having six arms perpendicular to each other, wherein each arm is connected to an assembly member that connects the center cross member with one of a plurality of center blocks; the plurality of center blocks, wherein each center block includes a plurality of wings formed along a base portion of the center block; a plurality of edge blocks, wherein each edge block includes a ridge structure that is formed to fit with the plurality of wings of the center block; and a plurality of corner blocks, wherein each corner block includes a protrusion structure that is formed to fit with the plurality of wings of the center block, wherein: (i) an edge track assembly that includes an edge track member and an edge holder member is formed on the ridge structure of each edge block; (ii) two protrusion structures of two corner blocks of the plurality of corner blocks are positioned to abut opposing ends of the edge track member of the edge track assembly of the edge block; and (iii) the edge holder member of the edge track assembly stabilizes the two protrusion structures that are positioned to abut opposing ends of the edge track member of the edge track assembly of the edge block.

    APPARATUS FOR DIAGNOSING DC-DC CONVERTER AND METHOD THEREOF
    9.
    发明申请
    APPARATUS FOR DIAGNOSING DC-DC CONVERTER AND METHOD THEREOF 有权
    用于诊断DC-DC转换器的方法及其方法

    公开(公告)号：US20110316524A1

    公开(公告)日：2011-12-29

    申请号：US12959769

    申请日：2010-12-03

    Applicant: Sung Kyu Kim ,  Jaewon Lee ,  Tae Hwan Chung ,  Ki Jong Lee ,  Jong Kyung Lim

    Inventor： Sung Kyu Kim ,  Jaewon Lee ,  Tae Hwan Chung ,  Ki Jong Lee ,  Jong Kyung Lim

    IPC: G01R19/18

    CPC classification number: G01R31/40 ,  H02M1/32

    Abstract: A diagnosis device and method of a voltage transformer can include a current transformer disposed at one side of an output port for generating a current variation according to an on/off operation of a power switch element; a first current detector configured to detect a forward direction current from the current transformer; a second current detector configured to detect a reverse direction current from the current transformer; a first voltage transformer configured to transform the forward direction current detected from the first current detector to a forward direction voltage; a second voltage transformer configured to transform the reverse direction current detected from the second current detector to a reverse direction voltage; and a diagnosis portion for comparing the forward direction voltage with the reverse direction voltage to determine whether or not an offset is formed.

    Abstract translation: 电压互感器的诊断装置和方法可以包括设置在输出端口一侧的电流互感器，用于根据功率开关元件的接通/断开操作产生电流变化; 第一电流检测器，被配置为检测来自电流互感器的正向电流; 第二电流检测器，被配置为检测来自电流互感器的反向电流; 第一电压变压器，被配置为将从第一电流检测器检测到的正向电流变换为正向电压; 被配置为将从第二电流检测器检测的反向电流变换为反向电压的第二电压互感器; 以及诊断部分，用于将正向电压与反向电压进行比较，以确定是否形成偏移。

    Method and apparatus for estimating pitch of signal
    10.
    发明授权
    Method and apparatus for estimating pitch of signal 有权
    用于估计信号音调的方法和装置

    公开(公告)号：US07672836B2

    公开(公告)日：2010-03-02

    申请号：US11247277

    申请日：2005-10-12

    Applicant: Yongbeom Lee ,  Yuan Yuan Shi ,  Jaewon Lee

    Inventor： Yongbeom Lee ,  Yuan Yuan Shi ,  Jaewon Lee

    IPC: G10L11/04

    CPC classification number: G10L25/90

    Abstract: A pitch estimating method and apparatus in which mixture Gaussian distributions based on candidate pitches having high period estimating values are generated, a mixture Gaussian distribution having a high likelihood is selected and dynamic programming is executed so that the pitch of the speech signal can be accurately estimated. The pitch estimating method comprises computing a normalized autocorrelation function of a windowed signal obtained by multiplying a frame of a speech signal by a window signal and determining candidate pitches from a peak value of the normalized autocorrelation function of the windowed signal, interpolating a period of the determined candidate pitches and a period estimating value representing a length of the period, generating Gaussian distributions for the candidate pitches for each frame for which the interpolated period estimating value is greater than a first threshold value, mixing the Gaussian distributions which are located at a distance less than a second threshold value to generate mixture Gaussian distributions and selecting at least one of the mixture Gaussian distributions that a likelihood exceeding a third threshold value, and executing dynamic programming for the frames to estimate the pitch of each frame, based on the candidate pitches of each of the frames and the selected mixture Gaussian distributions.

    Abstract translation: 一种音调估计方法和装置，其中生成具有高周期估计值的候选音调的混合高斯分布，选择具有高可能性的混合高斯分布，并且执行动态编程，使得语音信号的音调能够被精确估计 。 音调估计方法包括：计算通过将语音信号的帧乘以窗口信号而获得的加窗信号的标准化自相关函数，并根据窗口化信号的归一化自相关函数的峰值确定候选音高，内插 确定候选间距和表示周期长度的周期估计值，为内插周期估计值大于第一阈值的每个帧产生候选间距的高斯分布，将位于距离处的高斯分布混合 小于第二阈值以产生混合高斯分布，并且选择可能性超过第三阈值的混合高斯分布中的至少一个，并且基于候选音调执行帧估计每帧的音高的动态规划 的每个框架和se 选择混合高斯分布。

Patent Agency Ranking