公开(公告)号：US20160210551A1

公开(公告)日：2016-07-21

申请号：US14992129

申请日：2016-01-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hodong LEE ,  Hoshik LEE ,  Heeyoul CHOI ,  Yunhong MIN ,  Sang Hyun YOO ,  Yeha LEE ,  Jihyun LEE ,  YoungSang CHOI

IPC: G06N3/08 ,  G10L15/16 ,  G06F17/27 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06F17/27 ,  G06N3/04 ,  G06N3/0445 ,  G06N3/084 ,  G10L15/005 ,  G10L15/16 ,  G10L15/19

Abstract: A method and apparatus for training a language model, include generating a first training feature vector sequence and a second training feature vector sequence from training data. The method is configured to perform forward estimation of a neural network based on the first training feature vector sequence, and perform backward estimation of the neural network based on the second training feature vector sequence. The method is further configured to train a language model based on a result of the forward estimation and a result of the backward estimation.

Abstract translation: 一种用于训练语言模型的方法和装置，包括从训练数据生成第一训练特征向量序列和第二训练特征向量序列。 该方法被配置为基于第一训练特征向量序列执行神经网络的前向估计，并且基于第二训练特征向量序列执行神经网络的向后估计。 该方法还被配置为基于正向估计的结果和后向估计的结果来训练语言模型。

公开(公告)号：US20170229115A1

公开(公告)日：2017-08-10

申请号：US15493714

申请日：2017-04-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hoshik LEE ,  Heeyoul CHOI

IPC: G10L15/06 ,  G10L15/02 ,  G10L15/14 ,  G10L15/16 ,  G10L15/187

CPC classification number: G10L15/16 ,  G10L15/02 ,  G10L15/063 ,  G10L15/14 ,  G10L15/187 ,  G10L15/19 ,  G10L25/30

Abstract: A method and apparatus for training a neural network language model, and a method and apparatus for recognizing speech data based on a trained language model are provided. The method of training a language model involves converting, using a processor, training data into error-containing training data, and training a neural network language model using the error-containing training data.

公开(公告)号：US20180226078A1

公开(公告)日：2018-08-09

申请号：US15946840

申请日：2018-04-06

Applicant: Samsung Electronics Co., Ltd.

Inventor： Heeyoul CHOI ,  Hoshik LEE

IPC: G10L15/32

CPC classification number: G10L15/32 ,  G10L15/16 ,  G10L15/183 ,  G10L15/187 ,  G10L15/197

Abstract: A speech recognition method includes receiving a sentence generated through speech recognition, calculating a degree of suitability for each word in the sentence based on a relationship of each word with other words in the sentence, detecting a target word to be corrected among the words in the sentence based on the degree of suitability for each word, and replacing the target word with any one of candidate words corresponding to the target word.

公开(公告)号：US20160163310A1

公开(公告)日：2016-06-09

申请号：US14727462

申请日：2015-06-01

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hoshik LEE ,  Heeyoul CHOI

IPC: G10L15/16 ,  G10L15/06

CPC classification number: G10L15/16 ,  G10L15/02 ,  G10L15/063 ,  G10L15/14 ,  G10L15/187 ,  G10L15/19 ,  G10L25/30

Abstract: A method and apparatus for training a neural network language model, and a method and apparatus for recognizing speech data based on a trained language model are provided. The method of training a language model involves converting, using a processor, training data into error-containing training data, and training a neural network language model using the error-containing training data.

Abstract translation: 提供了一种用于训练神经网络语言模型的方法和装置，以及用于基于训练语言模型识别语音数据的方法和装置。 训练语言模型的方法包括使用处理器将训练数据转换为含错误的训练数据，以及使用含有错误的训练数据训练神经网络语言模型。

公开(公告)号：US20160196257A1

公开(公告)日：2016-07-07

申请号：US14749747

申请日：2015-06-25

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Heeyoul CHOI

IPC: G06F17/27 ,  G10L15/01 ,  G10L15/00 ,  G10L15/19

Abstract: A grammar correcting method is provided, the method including receiving a sentence generated based on speech recognition, receiving information associated with a speech recognition result of the sentence and correcting grammar in the sentence based on the information associated with the speech recognition results of the sentence.

Abstract translation: 提供了一种语法校正方法，该方法包括接收基于语音识别产生的句子，接收与句子的语音识别结果相关联的信息，并且基于与句子的语音识别结果相关联的信息来校正句子中的语法。

公开(公告)号：US20160155049A1

公开(公告)日：2016-06-02

申请号：US14704785

申请日：2015-05-05

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Heeyoul CHOI

IPC: G06N3/08

Abstract: Methods and apparatus for extending a neural network, reducing its dimension and processing input data are provided. The method of extending a neural network involves selecting, with a processor, a node of a neural network, adding a new node in a layer that includes the selected node, and setting connection weights of the new node based on connection weights of the selected node.

Abstract translation: 提供了扩展神经网络，减少其维数和处理输入数据的方法和装置。 扩展神经网络的方法涉及用处理器选择神经网络的节点，在包括所选节点的层中添加新节点，并且基于所选节点的连接权重来设置新节点的连接权重 。

公开(公告)号：US20160026913A1

公开(公告)日：2016-01-28

申请号：US14636684

申请日：2015-03-03

Applicant: Samsung Electronics Co., Ltd.

Inventor： Taesup MOON ,  Yeha LEE ,  Heeyoul CHOI

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04 ,  G06N3/0445 ,  G06N3/082

Abstract: A neural network training method based on training data, includes receiving training data including sequential data, and selecting a reference hidden node from hidden nodes in a neural network. The method further includes training the neural network based on remaining hidden nodes obtained by excluding the reference hidden node from the hidden nodes, and based on the training data, the remaining hidden nodes being connected with hidden nodes in a different time interval, and a connection between the reference hidden node and the hidden nodes in the different time interval being ignored.

Abstract translation: 一种基于训练数据的神经网络训练方法，包括接收包括顺序数据的训练数据，以及从神经网络中的隐藏节点中选择参考隐藏节点。 该方法还包括基于通过从隐藏节点排除参考隐藏节点获得的剩余隐藏节点来训练神经网络，并且基于训练数据，剩余的隐藏节点与不同时间间隔中的隐藏节点连接，以及连接 在不同时间间隔内的引用隐藏节点和隐藏节点之间被忽略。