公开(公告)号：US20080249774A1

公开(公告)日：2008-10-09

申请号：US12061156

申请日：2008-04-02

申请人： Hyun-Soo KIM ,  Myeong-gi Jeong ,  Hyun-Sik Shim ,  Young-Hee Park ,  Ha-Jin Yoo ,  Guen-Chang Kwak ,  Hye-Jin Kim ,  Kyung-Sook Bae

发明人： Hyun-Soo KIM ,  Myeong-gi Jeong ,  Hyun-Sik Shim ,  Young-Hee Park ,  Ha-Jin Yoo ,  Guen-Chang Kwak ,  Hye-Jin Kim ,  Kyung-Sook Bae

IPC分类号： G10L17/00

CPC分类号： G10L17/02

摘要： Disclosed is a method for speech speaker recognition of a speech speaker recognition apparatus, the method including detecting effective speech data from input speech; extracting an acoustic feature from the speech data; generating an acoustic feature transformation matrix from the speech data according to each of Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA), mixing each of the acoustic feature transformation matrixes to construct a hybrid acoustic feature transformation matrix, and multiplying the matrix representing the acoustic feature with the hybrid acoustic feature transformation matrix to generate a final feature vector; and generating a speaker model from the final feature vector, comparing a pre-stored universal speaker model with the generated speaker model to identify the speaker, and verifying the identified speaker.

摘要翻译： 公开了一种语音讲话者识别装置的语音说话人识别方法，该方法包括从输入语音中检测有效的语音数据; 从所述语音数据中提取声学特征; 根据主成分分析（PCA）和线性判别分析（LDA）中的每一个从语音数据生成声学特征变换矩阵，混合每个声学特征变换矩阵以构建混合声学特征变换矩阵，并将表示 声学特征与混合声学特征变换矩阵以产生最终特征向量; 以及从所述最终特征向量生成扬声器模型，将预先存储的通用扬声器模型与所产生的扬声器模型进行比较以识别所述扬声器，以及验证所识别的扬声器。

公开(公告)号：US20080101556A1

公开(公告)日：2008-05-01

申请号：US11928665

申请日：2007-10-30

申请人： Hyun-Soo KIM ,  Myeong-Gi JEONG ,  Young-Hee PARK

发明人： Hyun-Soo KIM ,  Myeong-Gi JEONG ,  Young-Hee PARK

IPC分类号： G10L15/00

CPC分类号： G10L15/01 ,  G10L25/00 ,  G10L2015/225

摘要： Provided are an apparatus and method for reporting speech recognition failures. The method includes detecting pure speech data from input speech data and outputting the detected pure speech data; checking at least one speech recognition failure for the pure speech data; and ascertaining speech recognition failure reasons from a check-result for the speech recognition failures and outputting the ascertained speech recognition failure reasons.

摘要翻译： 提供了用于报告语音识别失败的装置和方法。 该方法包括从输入语音数据检测纯语音数据并输出检测到的纯语音数据; 检查纯语音数据的至少一个语音识别失败; 并从语音识别失败的检查结果中确定语音识别失败原因并输出确定的语音识别失败原因。

公开(公告)号：US20100125680A1

公开(公告)日：2010-05-20

申请号：US12621180

申请日：2009-11-18

申请人： Hyun-Soo KIM ,  Jae-Ho KIM

发明人： Hyun-Soo KIM ,  Jae-Ho KIM

IPC分类号： G06F3/00

CPC分类号： H04W8/005 ,  H04W88/06

摘要： An apparatus and a method for providing an interworking service with a peripheral device in a Mobile Station (MS) supporting one or more wireless connectivity protocols are provided. Information on an execution environment of an application program for the interworking service is checked when the application program for performing the interworking service with the peripheral device is executed. A wireless connectivity protocol is selected from among the one or more wireless connectivity protocols for performing the interworking service with the peripheral device using the information on the execution environment of the application program.

摘要翻译： 提供了一种在支持一个或多个无线连接协议的移动台（MS）中提供与外围设备的互通服务的装置和方法。 当执行与外围设备的互通服务的应用程序被执行时，检查关于互通服务的应用程序的执行环境的信息。 从一个或多个无线连接协议中选择无线连接协议，用于使用关于应用程序的执行环境的信息来执行与外围设备的互通服务。

公开(公告)号：US20090279714A1

公开(公告)日：2009-11-12

申请号：US12436434

申请日：2009-05-06

申请人： Hyun-Soo KIM ,  Song-Suk Yook ,  Young-Kyu Cho ,  Woo-Jin Choi

发明人： Hyun-Soo KIM ,  Song-Suk Yook ,  Young-Kyu Cho ,  Woo-Jin Choi

IPC分类号： H04R3/00

CPC分类号： H04R3/005 ,  H04R2430/21

摘要： An apparatus and method for localizing a sound source in a robot are provided. The apparatus includes a microphone unit implemented by one or more microphones, which picks up a sound from a three-dimensional space. The apparatus also includes a sound source localizer for determining a position of the sound source in accordance with Time-Difference of Arrivals (TDOAs) and a highest power of the sound picked up by the microphone unit. Thus, the robot can rapidly and accurately localize the sound source in the three-dimensional space with minimum dead space, using a minimum number of microphones.

摘要翻译： 提供了一种用于在机器人中定位声源的装置和方法。 该装置包括由一个或多个麦克风实现的麦克风单元，其从三维空间拾取声音。 该装置还包括声源定位器，用于根据到达时差（TDOA）和由麦克风单元拾取的声音的最高功率来确定声源的位置。 因此，使用最小数量的麦克风，机器人可以以最小的死空间快速准确地定位三维空间中的声源。

公开(公告)号：US20080298599A1

公开(公告)日：2008-12-04

申请号：US12127867

申请日：2008-05-28

申请人： Hyun-Soo KIM

发明人： Hyun-Soo KIM

IPC分类号： H04R29/00

CPC分类号： H04R29/004 ,  G10L25/69

摘要： A system and method for evaluating performance of a microphone for long-distance speech recognition, which enables a robot to receive and respond to voices. A robot, which includes a network robot, must correctly recognize speech in order to recognize the user and to perceive its surroundings, objective evaluation criteria are required for choosing a microphone to be used in the robot. The methods include measuring a degree of attenuation of the voice, measuring a degree of distortion of the voice, and simultaneously measuring the degree of attenuation of the voice and the degree of distortion of the voice. A standard for the choice of a microphone, which can be digitalized, for a speech recognition function of a robot, permits choice of a microphone which has good sensitivity and can pick up voices without distortion when used at a large distance.

摘要翻译： 一种用于评估用于长距离语音识别的麦克风的性能的系统和方法，其使得机器人能够接收和响应语音。 包括网络机器人的机器人必须正确识别语音以便识别用户并感知其周围环境，因此需要客观的评估标准来选择要在机器人中使用的麦克风。 这些方法包括测量语音的衰减程度，测量语音的失真程度，同时测量语音的衰减程度和声音的失真程度。 用于机器人的语音识别功能的可以数字化的麦克风的选择的标准允许选择具有良好灵敏度的麦克风，并且可以在远距离使用时拾取语音而不失真。

公开(公告)号：US20080147383A1

公开(公告)日：2008-06-19

申请号：US11955483

申请日：2007-12-13

申请人： Hyun-Soo KIM

发明人： Hyun-Soo KIM

IPC分类号： G10L21/00 ,  G10L11/04

CPC分类号： G10L25/90

摘要： An apparatus and method for estimating audio signal spectrum information. The method including the steps of performing a morphological operation on a received audio signal, extracting peaks by using various peak extraction methods and extracting a remainder signal region from the extracted peaks, selecting a high-order peaks spectrum from the extracted remainder signal region. In addition, spectral envelopes are detected by performing an interpolation operation on the high-order peaks spectrum.

摘要翻译： 一种用于估计音频信号频谱信息的装置和方法。 该方法包括以下步骤：对所接收的音频信号执行形态学操作，通过使用各种峰值提取方法提取峰值并从提取的峰值提取余数信号区域，从提取的余数信号区域中选择高阶峰值频谱。 此外，通过对高阶峰值频谱进行插值运算来检测频谱包络。

公开(公告)号：US20130070575A1

公开(公告)日：2013-03-21

申请号：US13617474

申请日：2012-09-14

申请人： Hyun-Soo KIM ,  Jin Park ,  Kwang-Lae Kwak

发明人： Hyun-Soo KIM ,  Jin Park ,  Kwang-Lae Kwak

IPC分类号： G04G13/02

CPC分类号： G04G15/003 ,  G04G13/025

摘要： An alarm method in a portable terminal is provided, including setting an alarm by setting an alarm time, setting output information to be output at the alarm time, and setting an output device for receiving and displaying the output information; outputting a preset alarm sound when the set alarm time arrives, and obtaining the output information to be output at the alarm time; and transmitting the obtained output information to the set output device.

摘要翻译： 提供便携式终端中的报警方法，包括通过设置报警时间来设置报警，设置在报警时间输出的输出信息，以及设置用于接收和显示输出信息的输出装置; 当设定的报警时间到达时输出预设的报警声，并获得在报警时间输出的输出信息; 并将获得的输出信息发送到设置的输出设备。

公开(公告)号：US20100141758A1

公开(公告)日：2010-06-10

申请号：US12632101

申请日：2009-12-07

申请人： Hyun-Soo KIM ,  Sang-Ho KIM ,  Seong-Taek HWANG ,  Sang-Wook OH ,  Sung-Cheol KIM

发明人： Hyun-Soo KIM ,  Sang-Ho KIM ,  Seong-Taek HWANG ,  Sang-Wook OH ,  Sung-Cheol KIM

IPC分类号： H04N7/18 ,  G09G5/00

CPC分类号： H04N5/23296 ,  G06K9/20 ,  G09G5/00 ,  G09G5/227 ,  G09G2340/0407

摘要： A method is provided for automatically adjusting a size of characters using a camera. The method includes receiving an image with characters; adjusting a focus of the image with characters and detecting a region and a size of characters in the image; determining whether the size of the characters in the image falls within a preset range; recognizing the characters in the image and displaying the recognition results, if the size of characters falls within the preset range; and automatically adjusting a zoom ratio of the image and recognizing the characters in the resized image, if the size of the characters does not fall within the preset range.

摘要翻译： 提供了一种使用相机自动调整字符大小的方法。 该方法包括接收具有字符的图像; 用字符调整图像的焦点并检测图像中的字符的区域和大小; 确定图像中的字符的大小是否落在预设范围内; 识别图像中的字符并显示识别结果，如果字符的大小落在预设范围内; 并且如果字符的大小不在预设范围内，则自动调整图像的缩放倍数并识别被调整大小的图像中的字符。

公开(公告)号：US20090316999A1

公开(公告)日：2009-12-24

申请号：US12487378

申请日：2009-06-18

申请人： Hyun-Soo KIM ,  Seong-Taek Hwang ,  Sang-Wook Oh ,  Sang-Ho Kim ,  Yun-Je Oh ,  Hee-Won Jung ,  Sung-Cheol Kim

发明人： Hyun-Soo KIM ,  Seong-Taek Hwang ,  Sang-Wook Oh ,  Sang-Ho Kim ,  Yun-Je Oh ,  Hee-Won Jung ,  Sung-Cheol Kim

IPC分类号： G06K9/62 ,  H04N5/225

CPC分类号： G06K9/78 ,  G06K9/2081 ,  G06K9/228 ,  G06K9/325 ,  G06K9/723 ,  G06K2209/01

摘要： Disclosed is a method and an apparatus for recognizing characters using an image. A camera is activated according to a character recognition request and a preview mode is set for displaying an image photographed through the camera in real time. An auto focus of the camera is controlled and an image having a predetermined level of clarity is obtained for character recognition from the images obtained in the preview mode. The image for character recognition is character-recognition-processed so as to extract recognition result data. A final recognition character row is drawn that excludes non-character data from the recognition result data. A first word is combined including at least one character of the final recognition character row and a predetermined maximum number of characters. A dictionary database that stores dictionary information on various languages using the first word is searched, so as to provide the user with the corresponding word.

摘要翻译： 公开了一种使用图像识别字符的方法和装置。 根据字符识别请求激活相机，并且设置用于实时显示通过相机拍摄的图像的预览模式。 控制相机的自动对焦，并且从在预览模式中获得的图像中获得具有预定水平的清晰度的图像以进行字符识别。 用于字符识别的图像被字符识别处理，以便提取识别结果数据。 绘制从识别结果数据排除非字符数据的最终识别字符行。 组合第一个字，包括最终识别字符行的至少一个字符和预定的最大字符数。 搜索使用第一个单词存储各种语言的字典信息的词典数据库，以向用户提供对应的单词。

公开(公告)号：US20080042983A1

公开(公告)日：2008-02-21

申请号：US11768715

申请日：2007-06-26

申请人： Hyun-Soo KIM ,  Dae-Hyun Sim ,  Jae-Chan Koh ,  In-Kwon Kang ,  Kwan-Sic Kim ,  Young-Shik Shin ,  Jin-Choul Lee

发明人： Hyun-Soo KIM ,  Dae-Hyun Sim ,  Jae-Chan Koh ,  In-Kwon Kang ,  Kwan-Sic Kim ,  Young-Shik Shin ,  Jin-Choul Lee

IPC分类号： G06F3/041 ,  G06K9/00

CPC分类号： G06F3/03547 ,  G06F3/04886 ,  G06F2203/0338

摘要： Disclosed are a user input device and a method for rapidly selecting an operation mode in a mobile terminal having a touch screen input panel and a fingerprint recognition sensor. The user input method includes setting operation modes for at least one fingerprint data and input pattern, each comprised of keys necessary to implement a corresponding operation mode; detecting fingerprint data inputted from the fingerprint recognition sensor, and confirming an operation mode set for the inputted fingerprint data; and displaying an input pattern corresponding to the confirmed operation mode on the touch screen input panel.

摘要翻译： 公开了一种在具有触摸屏输入面板和指纹识别传感器的移动终端中快速选择操作模式的用户输入设备和方法。 用户输入方法包括设置至少一个指纹数据和输入模式的操作模式，每个指纹数据和输入模式包括实现相应操作模式所必需的按键; 检测从指纹识别传感器输入的指纹数据，并确认为输入的指纹数据设定的操作模式; 以及在触摸屏输入面板上显示与确认的操作模式相对应的输入模式。