专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

US20060122831A1 Speech recognition system for automatically controlling input level and speech recognition method using the same 审中-公开
标题翻译：用于自动控制输入电平和语音识别方法的语音识别系统
公开(公告)号：US20060122831A1
公开(公告)日：2006-06-08
申请号：US11262843
申请日：2005-11-01
申请人： Myeong-Gi Jeong , Hyun-Sik Shim , Jong-Chang Lee , Kwang-Choon Kim
发明人： Myeong-Gi Jeong , Hyun-Sik Shim , Jong-Chang Lee , Kwang-Choon Kim
IPC分类号： G10L15/00
CPC分类号： G10L25/78 , G10L2025/786 , H03G3/32
摘要： A speech recognition system comprises: a speech pickup element for picking up speech from an external speaker; a speech level controller for receiving the picked up speech at a speech input level provided by a speech recognizer, and outputting the received speech to the speech recognizer; a speech detector for detecting a speech signal period needed for speech recognition from the speech output from the speech receiver; a speech saturation detector for determining, based on the threshold value, whether the speech signal in the detected speech signal period is saturated; and an input level determiner for determining a new speech input level, and outputting information on the new speech input level to the speech receiver when the speech signal in the speech signal period is saturated, whereby the speech receiver receives the speech in a unsaturated state. A speech recognition method comprises steps corresponding to the functions of the system as specified above.
摘要翻译：语音识别系统包括：用于从外部扬声器拾取语音的语音拾取元件; 语音级控制器，用于在由语音识别器提供的语音输入电平上接收所拾取的语音，并将接收的语音输出到语音识别器; 语音检测器，用于从语音接收器输出的语音中检测语音识别所需的语音信号周期; 语音饱和检测器，用于基于所述阈值来确定所检测到的语音信号周期中的语音信号是否饱和; 以及用于确定新的语音输入电平的输入电平确定器，并且当语音信号周期中的语音信号饱和时，将关于新的语音输入电平的信息输出到语音接收机，由此语音接收机接收不饱和状态的语音。语音识别方法包括与上述系统的功能相对应的步骤。

2. 发明申请

US20070055527A1 Method for synthesizing various voices by controlling a plurality of voice synthesizers and a system therefor 审中-公开
标题翻译：通过控制多个语音合成器及其系统来合成各种语音的方法
公开(公告)号：US20070055527A1
公开(公告)日：2007-03-08
申请号：US11516865
申请日：2006-09-07
申请人： Myeong-Gi Jeong , Young-Hee Park , Jong-Chang Lee , Hyun-Sik Shim
发明人： Myeong-Gi Jeong , Young-Hee Park , Jong-Chang Lee , Hyun-Sik Shim
IPC分类号： G10L13/08
CPC分类号： G10L13/033
摘要： Disclosed is a voice synthesis system for performing various voice synthesis functions. At least one voice synthesizer synthesizes voices, and a TTS (Text-To-Speech) matching unit for controlling the voice synthesizer converts a text coming from a client apparatus into voices by analyzing the text. The system also includes a background sound mixer for mixing a background sound with the synthesized voices received from the voice synthesizer, and a modulation effective device for imparting sound-modulation effect to the synthesized voices. Thus, the system provides the user with more services by generating synthesized voices imparted with various effects.
摘要翻译：公开了一种用于执行各种语音合成功能的语音合成系统。至少一个语音合成器合成语音，并且用于控制语音合成器的TTS（文本到语音）匹配单元通过分析文本将来自客户端设备的文本转换成语音。该系统还包括用于将背景声音与从语音合成器接收的合成语音混合的背景混音器，以及用于对合成语音赋予声音调制效果的调制有效装置。因此，该系统通过产生具有各种效果的合成语音来向用户提供更多的服务。

3. 发明申请

US20060053009A1 Distributed speech recognition system and method 审中-公开
标题翻译：分布式语音识别系统及方法
公开(公告)号：US20060053009A1
公开(公告)日：2006-03-09
申请号：US11200203
申请日：2005-08-10
申请人： Myeong-Gi Jeong , Myeon-Kee Youn , Hyun-Sik Shim
发明人： Myeong-Gi Jeong , Myeon-Kee Youn , Hyun-Sik Shim
IPC分类号： G10L15/20
CPC分类号： G10L15/30 , G10L25/78
摘要： A distributed speech recognition system and method thereof in accordance with the present invention enables a word and a natural language to be recognized using detection of a pause period in a speech period in an inputted speech signal, and various groups of recognition vocabulary (for example, a home speech recognition vocabulary, a telematics vocabulary for a vehicle, a vocabulary for call center, and so forth) to be processed in the same speech recognition system by determining the recognition vocabulary required by a corresponding terminal using an identifier of the terminal since various terminals require various speech recognition targets. In addition, various types of channel distortion occurring due to the type of terminal and the recognition environment are minimized by adapting them to a speech database model using a channel estimation method so that the speech recognition performance is enhanced.
摘要翻译：根据本发明的分布式语音识别系统及其方法使得能够使用输入的语音信号中的语音周期中的暂停时段的检测来识别单词和自然语言，以及各种识别词汇组（例如，家庭语音识别词汇，用于车辆的远程信息处理词汇表，呼叫中心的词汇表等）在同一语音识别系统中通过使用终端的标识符来确定相应终端所需的识别词汇，因为各种终端需要各种语音识别目标。此外，通过使用信道估计方法使它们适应于语音数据库模型，使得由于终端类型和识别环境而发生的各种类型的信道失真被最小化，从而增强了语音识别性能。

4. 发明申请

US20080249774A1 METHOD AND APPARATUS FOR SPEECH SPEAKER RECOGNITION 审中-公开
标题翻译：用于语音识别的方法和装置
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。

5. 发明申请

US20060268785A1 Wireless communication system and method for preventing mutual interference between wireless communication channels 审中-公开
标题翻译：用于防止无线通信信道之间的相互干扰的无线通信系统和方法
公开(公告)号：US20060268785A1
公开(公告)日：2006-11-30
申请号：US11439942
申请日：2006-05-24
申请人： Jong-Ho Park , Hyun-Sik Shim , Jong-Chang Lee
发明人： Jong-Ho Park , Hyun-Sik Shim , Jong-Chang Lee
IPC分类号： H04Q7/00
CPC分类号： H04W36/12
摘要： Disclosed is a method for preventing mutual interference between wireless communication channels in a wireless communication system that includes at least one station, at least one AP connected to said at least one station, and a server. The method includes periodically checking by each AP wireless communication connection information on wireless communication setup with said at least one station; receiving by the server the wireless communication connection information from said at least one AP; analyzing by the server the received wireless communication connection information, determining if there exist an AP and stations connected to the AP, and generating a setup change message; transmitting by the server the generated setup change message to the AP and the stations; and receiving by the AP and the stations connected to the AP the setup change message, and changing the wireless communication setup based on the setup change message.
摘要翻译：公开了一种防止无线通信系统中的无线通信信道之间的相互干扰的方法，所述无线通信系统包括至少一个站，连接到所述至少一个站的至少一个AP和服务器。该方法包括通过每个AP无线通信连接周期性地检查与所述至少一个站的无线通信建立的信息; 由所述服务器接收来自所述至少一个AP的无线通信连接信息; 由服务器分析接收到的无线通信连接信息，确定是否存在连接到AP的AP和站，并生成建立改变消息; 由服务器发送生成的设置更改消息给AP和站; 以及由AP和连接到AP的站接收设置改变消息，以及基于设置改变消息来改变无线通信建立。

6. 发明申请

US20060104517A1 Template-based face detection method 审中-公开
标题翻译：基于模板的人脸检测方法
公开(公告)号：US20060104517A1
公开(公告)日：2006-05-18
申请号：US11262842
申请日：2005-11-01
申请人： Byoung-Chul Ko , Jong-Chang Lee , Hyun-Sik Shim
发明人： Byoung-Chul Ko , Jong-Chang Lee , Hyun-Sik Shim
IPC分类号： G06K9/62 , G06K9/36
CPC分类号： G06K9/00228
摘要： A template-based face detection method includes: producing an average face image from a face database, wavelet-converting the produced face image, and removing a low frequency component of high and low frequency components of the converted image, the low frequency component being sensitive to illumination; producing a face template with only high horizontal and vertical frequency components of the high frequency components; and retrieving an initial face position using the face template when an image is inputted, and detecting the face in a next frame by using, as a face template for the next frame, a template obtained by linearly combining the face template with a high frequency wavelet coefficient corresponding to the position of the face in a current frame. Thus, the method has a shortened calculation time for face detection, and can accurately detect a face irrespective of skin color and illumination.
摘要翻译：基于模板的人脸检测方法包括：从面部数据库产生平均脸部图像，对产生的面部图像进行小波变换，以及去除转换图像的高频和低频分量的低频分量，低频分量敏感照明; 产生仅具有高频分量的高水平和垂直频率分量的面模板; 以及当输入图像时使用面部模板检索初始面部位置，并且通过使用作为下一帧的面部模板来检测下一帧中的脸部，通过将面部模板与高频小波线性组合而获得的模板对应于当前帧中的脸部位置的系数。因此，该方法具有缩短的脸部检测的计算时间，并且可以准确地检测脸部，而与肤色和照明无关。

7. 发明申请

US20120271901A1 METHOD AND APPARATUS FOR CONNECTING DEVICES 审中-公开
标题翻译：用于连接设备的方法和装置
公开(公告)号：US20120271901A1
公开(公告)日：2012-10-25
申请号：US13452766
申请日：2012-04-20
申请人： Kwang-Min Kim , Jong-Chang Lee , Won-Joo Park , Hyun-Sik Shim , Young-Hee Park , Moon-Sang Lee , Min-Soo Koo , Seung-Hyun Yoon , Ji-In Nam
发明人： Kwang-Min Kim , Jong-Chang Lee , Won-Joo Park , Hyun-Sik Shim , Young-Hee Park , Moon-Sang Lee , Min-Soo Koo , Seung-Hyun Yoon , Ji-In Nam
IPC分类号： G06F15/16
CPC分类号： H04L67/24 , H04L12/2825 , H04L67/025
摘要： A system and method for connecting devices includes receiving from a first device a request to follow a second device, and setting a following relationship between the first device and the second device in response to the request.
摘要翻译：用于连接设备的系统和方法包括：从第一设备接收跟随第二设备的请求，以及响应于该请求，设置第一设备和第二设备之间的跟随关系。

8. 发明申请

US20060155421A1 System and method for controlling movement of movable terminal for MiniCon 审中-公开
标题翻译： MiniCon可移动终端运动控制系统及方法
公开(公告)号：US20060155421A1
公开(公告)日：2006-07-13
申请号：US11322266
申请日：2006-01-03
申请人： Seung-Hyun Baek , Hyun-Sik Shim , Jong-Chang Lee
发明人： Seung-Hyun Baek , Hyun-Sik Shim , Jong-Chang Lee
IPC分类号： G01M1/38 , G05B13/00
CPC分类号： G05D1/0274 , G05D1/0225 , G05D1/0242 , G05D1/0246 , G05D23/1919
摘要： In a system and method for controlling the movement of a movable terminal for a MiniCon through a network, a temperature in a number of partitioned indoor spaces is maintained within a set temperature range desired by a user while the terminal moves in the indoor spaces. The system is provided with at least one MiniCon which performs air-conditioning, and includes: a movable terminal which docks with the MiniCon, and which moves along a predetermined path; and a server which communicates with the movable terminal via a local area network. The server sends, to the movable terminal, a control command for performance of air-conditioning in indoor spaces along the predetermined path. Accordingly, the MiniCon is enabled to freely move into at least one of a number of indoor spaces, and to perform air-conditioning, thereby improving air-conditioning efficiency and maximizing user convenience.
摘要翻译：在用于通过网络控制MiniCon的可移动终端的运动的系统和方法中，当终端在室内空间中移动时，多个分隔的室内空间中的温度保持在用户期望的设定温度范围内。该系统设置有至少一个执行空调的MiniCon，并且包括：可移动终端，其与MiniCon对接并且沿预定路径移动; 以及经由局域网与可移动终端进行通信的服务器。服务器向可动终端发送用于沿着预定路径在室内空间中执行空调的控制命令。因此，MiniCon能够自由移动到多个室内空间中的至少一个，并且进行空调，从而提高空调效率并最大化用户便利性。

9. 发明申请

US20100329511A1 Apparatus and method for detecting hands of subject in real time 有权
标题翻译：用于实时检测被摄体的手的装置和方法
公开(公告)号：US20100329511A1
公开(公告)日：2010-12-30
申请号：US12803369
申请日：2010-06-25
申请人： Je-Han Yoon , Hee-Jun Song , Hyun-Sik Shim , Young-Hee Park , Jae-Wook Jeon , Tae-Houn Song , Cong-Thien Pham , Seung-Hun Jin , Duc-Dung Nguyen
发明人： Je-Han Yoon , Hee-Jun Song , Hyun-Sik Shim , Young-Hee Park , Jae-Wook Jeon , Tae-Houn Song , Cong-Thien Pham , Seung-Hun Jin , Duc-Dung Nguyen
IPC分类号： G06K9/00
CPC分类号： G06K9/00382
摘要： An apparatus and method can effectively detect both hands and hand shape of a user from images input through cameras. A skin image detecting skin regions from one of the input images and a stereoscopic distance image are used. For hand detection, background and noise are eliminated from a combined image of the skin image and the distance image and regions corresponding to actual both hands are detected from effective images having a high probability of hands. For hand shape detection, a non-skin region is eliminated from the skin image based on the stereoscopic distance information, hand shape candidate regions are detected from the remaining region after elimination, and finally a hand shape is determined.
摘要翻译：一种装置和方法可以通过相机输入的图像有效地检测用户的手和手的形状。使用从输入图像之一和立体距离图像检测皮肤区域的皮肤图像。对于手部检测，从皮肤图像的组合图像中消除背景和噪声，并且从具有高概率手的有效图像检测距离图像和对应于实际双手的区域。对于手形检测，基于立体距离信息从皮肤图像中去除非皮肤区域，从消除后的剩余区域检测手形候补区域，最后确定手形。

10. 发明申请

US20080273766A1 FACE RECOGNITION SYSTEM AND METHOD BASED ON ADAPTIVE LEARNING 有权
标题翻译：基于自适应学习的面部识别系统和方法
公开(公告)号：US20080273766A1
公开(公告)日：2008-11-06
申请号：US12115250
申请日：2008-05-05
申请人： Hyun-Soo Kim , Je-Han Yoon , Hyun-Sik Shim , Young-Hee Park , Do-Hyung Kim , Woo-Han Yun
发明人： Hyun-Soo Kim , Je-Han Yoon , Hyun-Sik Shim , Young-Hee Park , Do-Hyung Kim , Woo-Han Yun
IPC分类号： G06K9/00
CPC分类号： G06K9/00295
摘要： A face recognition system based on adaptive learning includes a specific person detection and tracking unit for detecting and tracking a specific person from a moving image. A facial feature extraction unit extracts a plurality of facial feature vectors from the detected and tracked specific person. A face recognition unit searches for a given registration model by comparing the extracted facial feature vectors with facial feature vectors of the registration models previously stored in a user registration model database. A learning target selection unit selects a facial feature vector to be added to a record of the given registration model from among the extracted facial feature vectors. A registration model learning unit adds and updates the selected facial feature vector to the record of the given registration model.
摘要翻译：基于自适应学习的面部识别系统包括用于从运动图像中检测和跟踪特定人物的特定人物检测和跟踪单元。面部特征提取单元从检测到和跟踪的特定人物中提取多个面部特征向量。面部识别单元通过将提取的面部特征向量与先前存储在用户登记模型数据库中的登记模型的面部特征向量进行比较来搜索给定的登记模型。学习目标选择单元从所提取的面部特征向量中选择要添加到给定登记模型的记录的面部特征向量。注册模型学习单元将所选择的面部特征向量添加并更新到给定注册模型的记录。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式