-
公开(公告)号：US20220171631A1
公开(公告)日：2022-06-02
申请号：US17538147
申请日：2021-11-30
Inventor： Ju-Yeob KIM , Jin Ho HAN
IPC: G06F9/38
Abstract: A method for processing floating point operations in a multi-processor system including a plurality of single processor cores is provided. In this method, upon receiving a group setting for performing an operation, the plurality of single processor cores are grouped into at least one group according to the group setting, and a single processor core set as a master in the group loads an instruction for performing the operation from an external memory, and performs parallel operations by utilizing floating point units (FUPs) of all single processor cores in the group according to the instructions.
-
2.发明申请METHOD AND APPARATUS FOR SERIAL BUS COMMUNICATION BASED ON ORTHOGONAL SIGNAL WAVEFORM 审中-公开基于正交信号波形的串行总线通信方法与装置公开(公告)号：US20160036608A1
公开(公告)日：2016-02-04
申请号：US14742421
申请日：2015-06-17
Inventor： Joo Hyun LEE , Ju-Yeob KIM
CPC classification number: H04L12/40 , H04L25/4921
Abstract: A first communication device is provided. The first communication device modulates data to generate a first data symbol. The first communication device generates a first signal by using a first signal waveform allocated among a plurality of mutually orthogonal signal waveforms and the first data symbol. The first communication device outputs the first signal to a serial line connected to a second communication device.
Abstract translation: 提供第一通信设备。 第一通信设备调制数据以产生第一数据符号。 第一通信装置通过使用在多个相互正交的信号波形中分配的第一信号波形和第一数据符号来生成第一信号。 第一通信设备将第一信号输出到连接到第二通信设备的串行线路。
-
3.发明公开公开(公告)号：US20240062809A1
公开(公告)日：2024-02-22
申请号：US18499634
申请日：2023-11-01
Inventor： Jin-Ho HAN , Byung-Jo KIM , Ju-Yeob KIM , Hye-Ji KIM , Joo-Hyun LEE , Seong-Min KIM
IPC: G11C11/4096 , G06F7/544 , G06N3/063 , G11C11/4093 , G11C11/54
CPC classification number: G11C11/4096 , G06F7/5443 , G06N3/063 , G11C11/4093 , G11C11/54
Abstract: Disclosed herein is an Artificial Intelligence (AI) processor. The AI processor includes multiple NVM AI cores for respectively performing basic unit operations required for a deep-learning operation based on data stored in NVM; SRAM for storing at least some of the results of the basic unit operations; and an AI core for performing an accumulation operation on the results of the basic unit operation.
-
公开(公告)号：US20210157734A1
公开(公告)日：2021-05-27
申请号：US16953242
申请日：2020-11-19
Inventor： Byung Jo KIM , Joo Hyun LEE , Seong Min KIM , Ju-Yeob KIM , Jin Kyu KIM , Mi Young LEE
IPC: G06F12/0862 , G06F12/02 , G06F13/16 , G06N3/063
Abstract: 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.
-
公开(公告)号：US20200151568A1
公开(公告)日：2020-05-14
申请号：US16541275
申请日：2019-08-15
Inventor： Mi Young LEE , Byung Jo KIM , Seong Min KIM , Ju-Yeob KIM , Jin Kyu KIM , Joo Hyun LEE
Abstract: 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.
-
Patent Agency Ranking
公开(公告)号：US20150279385A1
公开(公告)日：2015-10-01
申请号：US14667675
申请日：2015-03-24
Inventor： Ju-Yeob KIM , Bon-Tae KOO , Tae-Joong KIM
CPC classification number: G10L15/20 , G10L15/02 , G10L21/0208 , G10L25/24
Abstract: 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.
Abstract translation: 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。 标准语音传输单元生成标准语音。 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。
-
公开(公告)号：US20210357753A1
公开(公告)日：2021-11-18
申请号：US17317607
申请日：2021-05-11
Inventor： Jin Kyu KIM , Byung Jo KIM , Seong Min KIM , Ju-Yeob KIM , Ki Hyuk PARK , Mi Young LEE , Joo Hyun LEE , Young-deuk JEON , Min-Hyung CHO
Abstract: A method and apparatus for multi-level stepwise quantization for neural network are provided. The apparatus sets a reference level by selecting a value from among values of parameters of the neural network in a direction from a high value equal to or greater than a predetermined value to a lower value, and performs learning based on the reference level. The setting of a reference level and the performing of learning are iteratively performed until the result of the reference level learning satisfies a predetermined value and there is no variable parameter that is updated during learning among the parameters.
-
公开(公告)号：US20180268571A1
公开(公告)日：2018-09-20
申请号：US15698499
申请日：2017-09-07
Inventor： Seong Mo PARK , Sung Eun KIM , Ju-Yeob KIM , Jin Kyu KIM , Kwang Il OH , Joo Hyun LEE
CPC classification number: G06T9/002 , G06T7/11 , G06T7/194 , G06T2200/28 , G06T2207/20081 , G06T2207/20084
Abstract: 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.
-
公开(公告)号：US20160232892A1
公开(公告)日：2016-08-11
申请号：US14991716
申请日：2016-01-08
Inventor： Yun-Joo KIM , Ju-Yeob KIM , Tae-Joong KIM
IPC: G10L15/06 , G10L15/183 , G10L15/02 , G06F17/27 , G10L15/14
CPC classification number: G10L15/063 , G10L15/14 , G10L2015/025 , G10L2015/027 , G10L2015/0633 , G10L2015/0635
Abstract: Disclosed herein are a method and an apparatus of expanding a speech recognition database used for speech recognition. The method of expanding a speech recognition database includes generating a pronunciation text from a corpus; confirming whether or not a non-registered word that is not registered in advance in a pronunciation dictionary among words included in the pronunciation text is present; generating lexical model information on the corresponding non-registered word with reference to a built-up acoustic model in the case in which the non-registered word is present as a confirmation result; and adding the generated lexical model information to a built-up lexical model. According to exemplary embodiments of the present invention, various speeches may be recognized in a stand-along speech recognizer in which an infrastructure is insufficient.
Abstract translation: 这里公开了扩展用于语音识别的语音识别数据库的方法和装置。 扩展语音识别数据库的方法包括从语料库生成发音文本; 确认在发音文本中包含的字之间是否存在在发音字典中未预先注册的未注册字; 在存在非注册字的情况下，参考建立的声学模型，在对应的非注册字上产生词汇模型信息作为确认结果; 并将生成的词汇模型信息添加到已建立的词汇模型中。 根据本发明的示例性实施例，可以在基础设施不足的独立语音识别器中识别各种语音。
-
公开(公告)号：US20150294667A1
公开(公告)日：2015-10-15
申请号：US14681187
申请日：2015-04-08
Inventor： Tae-Joong KIM , Ju-Yeob KIM
IPC: G10L15/20
CPC classification number: G10L21/034 , G10L21/0224 , G10L21/0232
Abstract: 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.
Abstract translation: 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。
-
-
-
-
-
-
-
-
-
Search Results
17
records
(took 0.02 seconds)
