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. 发明授权

US11449720B2 Image recognition device, operating method of image recognition device, and computing device including image recognition device 有权
公开(公告)号：US11449720B2
公开(公告)日：2022-09-20
申请号：US16870412
申请日：2020-05-08
申请人： ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
发明人： Ju-Yeob Kim , Byung Jo Kim , Seong Min Kim , Jin Kyu Kim , Ki Hyuk Park , Mi Young Lee , Joo Hyun Lee , Young-deuk Jeon , Min-Hyung Cho
IPC分类号： G06K9/62
摘要： Provided is an image recognition device. The image recognition device includes a frame data change detector that sequentially receives a plurality of frame data and detects a difference between two consecutive frame data, an ensemble section controller that sets an ensemble section in the plurality of frame data, based on the detected difference, an image recognizer that sequentially identifies classes respectively corresponding to a plurality of section frame data by applying different neural network classifiers to the plurality of section frame data in the ensemble section, and a recognition result classifier that sequentially identifies ensemble classes respectively corresponding to the plurality of section frame data by combining the classes in the ensemble section.

2. 发明授权

US11455539B2 Quantization method and device for weights of batch normalization layer 有权
公开(公告)号：US11455539B2
公开(公告)日：2022-09-27
申请号：US16541275
申请日：2019-08-15
申请人： ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
发明人： Mi Young Lee , Byung Jo Kim , Seong Min Kim , Ju-Yeob Kim , Jin Kyu Kim , Joo Hyun Lee
IPC分类号： G06N3/08 , G06F17/18
摘要： An embodiment of the present invention provides a quantization method for weights of a plurality of batch normalization layers, including: receiving a plurality of previously learned first weights of the plurality of batch normalization layers; obtaining first distribution information of the plurality of first weights; performing a first quantization on the plurality of first weights using the first distribution information to obtain a plurality of second weights; obtaining second distribution information of the plurality of second weights; and performing a second quantization on the plurality of second weights using the second distribution information to obtain a plurality of final weights, and thereby reducing an error that may occur when quantizing the weight of the batch normalization layer.

3. 发明授权

US11003985B2 Convolutional neural network system and operation method thereof 有权
公开(公告)号：US11003985B2
公开(公告)日：2021-05-11
申请号：US15806111
申请日：2017-11-07
申请人： ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
发明人： Jin Kyu Kim , Byung Jo Kim , Seong Min Kim , Ju-Yeob Kim , Mi Young Lee , Joo Hyun Lee
IPC分类号： G06N3/063 , G06F7/544 , G06N3/04 , G06F17/15 , G06N3/08
摘要： Provided is a convolutional neural network system including a data selector configured to output an input value corresponding to a position of a sparse weight from among input values of input data on a basis of a sparse index indicating the position of a nonzero value in a sparse weight kernel, and a multiply-accumulate (MAC) computator configured to perform a convolution computation on the input value output from the data selector by using the sparse weight kernel.

4. 发明授权

US11488003B2 Artificial neural network apparatus and operating method for the same 有权
公开(公告)号：US11488003B2
公开(公告)日：2022-11-01
申请号：US16409437
申请日：2019-05-10
申请人： ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
发明人： Ju-Yeob Kim , Byung Jo Kim , Seong Min Kim , Jin Kyu Kim , Mi Young Lee , Joo Hyun Lee
IPC分类号： G06K9/62 , G06N3/063 , G06F9/30 , G06N3/04 , G06V10/82
摘要： An artificial neural network apparatus and an operating method including a plurality of layer processors for performing operations on input data are disclosed. The artificial neural network apparatus may include: a flag layer processor for outputting a flag according to a comparison result between a pooling output value of a current frame and a pooling output value of a previous frame; and a controller for stopping operation of a layer processor which performs operations after the flag layer processor among the plurality of layer processors when the flag is outputted from the flag layer processor, wherein the flag layer processor is a layer processor that performs a pooling operation first among the plurality of layer processors.

5. 发明授权

US10319115B2 Image compression device 有权
公开(公告)号：US10319115B2
公开(公告)日：2019-06-11
申请号：US15698499
申请日：2017-09-07
申请人： ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
发明人： Seong Mo Park , Sung Eun Kim , Ju-Yeob Kim , Jin Kyu Kim , Kwang Il Oh , Joo Hyun Lee
IPC分类号： G06T9/00 , G06T7/11 , G06T7/194
摘要： Provided is an image compression device including an object extracting unit configured to perform convolution neural network (CNN) training and identify an object from an image received externally, a parameter adjusting unit configured to adjust a quantization parameter of a region in which the identified object is included in the image on the basis of the identified object, and an image compression unit configured to compress the image on the basis of the adjusted quantization parameter.

6. 发明授权

US09311916B2 Apparatus and method for improving voice recognition 有权
标题翻译：改善语音识别的装置和方法
公开(公告)号：US09311916B2
公开(公告)日：2016-04-12
申请号：US14667675
申请日：2015-03-24
申请人： ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
发明人： Ju-Yeob Kim , Bon-Tae Koo , Tae-Joong Kim
IPC分类号： G10L21/02 , G10L15/18 , G10L15/20 , G10L15/02 , G10L21/0208 , G10L25/24
CPC分类号： G10L15/20 , G10L15/02 , G10L21/0208 , G10L25/24
摘要： An apparatus and method for improving voice recognition are disclosed herein. The apparatus includes a standard voice transmission unit, a Mel-frequency cepstrum coefficient (MFCC) generation unit, and an MFCC compensation unit. The standard voice transmission unit generates a standard voice. The MFCC generation unit generates voice feature data (MFCC) based on the utterance of the standard voice before voice recognition. The MFCC compensation unit stores a gain value generated based on the standard voice, and compensates for the distortion of the voice feature data based on the utterance of a user using the gain value during the voice recognition.
摘要翻译：本文公开了一种用于改善语音识别的装置和方法。该装置包括标准语音发送单元，梅尔频率倒谱系数（MFCC）生成单元和MFCC补偿单元。标准语音传输单元产生标准语音。 MFCC生成单元基于语音识别之前的标准语音的发音来生成语音特征数据（MFCC）。 MFCC补偿单元存储基于标准语音生成的增益值，并且基于在语音识别期间使用增益值的用户的话语来补偿语音特征数据的失真。

7. 发明授权

US11494630B2 Neuromorphic arithmetic device and operating method thereof 有权
公开(公告)号：US11494630B2
公开(公告)日：2022-11-08
申请号：US16742808
申请日：2020-01-14
申请人： ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
发明人： Young-deuk Jeon , Byung Jo Kim , Ju-Yeob Kim , Jin Kyu Kim , Ki Hyuk Park , Mi Young Lee , Joo Hyun Lee , Min-Hyung Cho
IPC分类号： G06N3/063 , G06F7/575 , G06F17/15
摘要： The neuromorphic arithmetic device comprises an input monitoring circuit that outputs a monitoring result by monitoring that first bits of at least one first digit of a plurality of feature data and a plurality of weight data are all zeros, a partial sum data generator that skips an arithmetic operation that generates a first partial sum data corresponding to the first bits of a plurality of partial sum data in response to the monitoring result while performing the arithmetic operation of generating the plurality of partial sum data, based on the plurality of feature data and the plurality of weight data, and a shift adder that generates the first partial sum data with a zero value and result data, based on second partial sum data except for the first partial sum data among the plurality of partial sum data and the first partial sum data generated with the zero value.

8. 发明授权

US11204876B2 Method and apparatus for controlling memory using prefetch information 有权
公开(公告)号：US11204876B2
公开(公告)日：2021-12-21
申请号：US16953242
申请日：2020-11-19
申请人： ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
发明人： Byung Jo Kim , Joo Hyun Lee , Seong Min Kim , Ju-Yeob Kim , Jin Kyu Kim , Mi Young Lee
IPC分类号： G06F12/08 , G06F12/0862 , G06N3/063 , G06F13/16 , G06F12/02
摘要： A method for controlling a memory from which data is transferred to a neural network processor and an apparatus thereof are provided, the method including: generating prefetch information of data by using a blob descriptor and a reference prediction table after history information is input; reading the data in the memory based on the pre-fetch information and temporarily archiving read data in a prefetch buffer; and accessing next data in the memory based on the prefetch information and temporarily archiving the next data in the prefetch buffer after the data is transferred to the neural network from the prefetch buffer.

9. 发明授权

US09583120B2 Noise cancellation apparatus and method 有权
标题翻译：噪声消除装置及方法
公开(公告)号：US09583120B2
公开(公告)日：2017-02-28
申请号：US14681187
申请日：2015-04-08
申请人： ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE
发明人： Tae-Joong Kim , Ju-Yeob Kim
IPC分类号： G10L21/0208 , G10L21/0232 , G10L21/034 , G10L21/0224
CPC分类号： G10L21/034 , G10L21/0224 , G10L21/0232
摘要： Disclosed herein is a noise cancellation apparatus and method, which select in advance parameters to be used for noise cancellation in a reference voice signal section by generating a reference voice signal in advance before a voice signal is generated, thus improving noise cancellation effects. The noise cancellation apparatus includes a parameter initialization unit for determining an initial value of a parameter to be used for noise cancellation, based on reference signals filtered for respective frequencies, a parameter estimation unit for receiving the initial value of the parameter, and estimating the parameter in response to signals that are input after being filtered for respective frequencies, a gain estimation unit for calculating gains for respective frequencies based on the parameter from the parameter estimation unit, and a gain application unit for cancelling noise by applying the gains to the signals that are input after being filtered for respective frequencies.
摘要翻译：这里公开了一种噪声消除装置和方法，其通过在生成语音信号之前预先生成参考语音信号，预先选择参考语音信号部分中用于噪声消除的参数，从而改善噪声消除效果。噪声消除装置包括：参数初始化单元，用于基于针对各个频率滤波的参考信号，确定要用于噪声消除的参数的初始值;参数估计单元，用于接收参数的初始值，以及估计参数响应于在针对各个频率被滤波后输入的信号，增益估计单元，用于基于来自参数估计单元的参数计算各个频率的增益，以及增益应用单元，用于通过将增益应用于在对各个频率进行滤波后输入。

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