公开(公告)号：US10402494B2

公开(公告)日：2019-09-03

申请号：US15439416

申请日：2017-02-22

Applicant: Electronics and Telecommunications Research Institute

Inventor： Eui Sok Chung ,  Byung Ok Kang ,  Ki Young Park ,  Jeon Gue Park ,  Hwa Jeon Song ,  Sung Joo Lee ,  Yun Keun Lee ,  Hyung Bae Jeon

IPC: G06F17/27 ,  G06F17/28

Abstract: Provided is a method of automatically expanding input text. The method includes receiving input text composed of a plurality of documents, extracting a sentence pair that is present in different documents among the plurality of documents, setting the extracted sentence pair as an input of an encoder of a sequence-to-sequence model, setting an output of the encoder as an output of a decoder of the sequence-to-sequence model and generating a sentence corresponding to the input, and generating expanded text based on the generated sentence.

公开(公告)号：US20180157640A1

公开(公告)日：2018-06-07

申请号：US15439416

申请日：2017-02-22

Applicant: Electronics and Telecommunications Research Institute

Inventor： Eui Sok CHUNG ,  Byung Ok Kang ,  Ki Young Park ,  Jeon Gue Park ,  Hwa Jeon Song ,  Sung Joo Lee ,  Yun Keun Lee ,  Hyung Bae Jeon

IPC: G06F17/27

CPC classification number: G06F17/2775 ,  G06F17/2881

Abstract: Provided is a method of automatically expanding input text. The method includes receiving input text composed of a plurality of documents, extracting a sentence pair that is present in different documents among the plurality of documents, setting the extracted sentence pair as an input of an encoder of a sequence-to-sequence model, setting an output of the encoder as an output of a decoder of the sequence-to-sequence model and generating a sentence corresponding to the input, and generating expanded text based on the generated sentence.

公开(公告)号：US10789332B2

公开(公告)日：2020-09-29

申请号：US16121836

申请日：2018-09-05

Applicant: Electronics and Telecommunications Research Institute

Inventor： Hoon Chung ,  Jeon Gue Park ,  Sung Joo Lee ,  Yun Keun Lee

IPC: G06F17/17 ,  G06N3/04

Abstract: Provided are an apparatus and method for linearly approximating a deep neural network (DNN) model which is a non-linear function. In general, a DNN model shows good performance in generation or classification tasks. However, the DNN fundamentally has non-linear characteristics, and therefore it is difficult to interpret how a result from inputs given to a black box model has been derived. To solve this problem, linear approximation of a DNN is proposed. The method for linearly approximating a DNN model includes 1) converting a neuron constituting a DNN into a polynomial, and 2) classifying the obtained polynomial as a polynomial of input signals and a polynomial of weights.

公开(公告)号：US20190272309A1

公开(公告)日：2019-09-05

申请号：US16121836

申请日：2018-09-05

Applicant: Electronics and Telecommunications Research Institute

Inventor： Hoon Chung ,  Jeon Gue Park ,  Sung Joo Lee ,  Yun Keun Lee

IPC: G06F17/17 ,  G06N3/04

Abstract: Provided are an apparatus and method for linearly approximating a deep neural network (DNN) model which is a non-linear function. In general, a DNN model shows good performance in generation or classification tasks. However, the DNN fundamentally has non-linear characteristics, and therefore it is difficult to interpret how a result from inputs given to a black box model has been derived. To solve this problem, linear approximation of a DNN is proposed. The method for linearly approximating a DNN model includes 1) converting a neuron constituting a DNN into a polynomial, and 2) classifying the obtained polynomial as a polynomial of input signals and a polynomial of weights.

公开(公告)号：US10089979B2

公开(公告)日：2018-10-02

申请号：US14737907

申请日：2015-06-12

Applicant: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

Inventor： Hoon Chung ,  Jeon Gue Park ,  Sung Joo Lee ,  Yun Keun Lee

IPC: G10L15/00 ,  G10L15/16

Abstract: Provided are a signal processing algorithm-integrated deep neural network (DNN)-based speech recognition apparatus and a learning method thereof. A model parameter learning method in a deep neural network (DNN)-based speech recognition apparatus implementable by a computer includes converting a signal processing algorithm for extracting a feature parameter from a speech input signal of a time domain into signal processing deep neural network (DNN), fusing the signal processing DNN and a classification DNN, and learning a model parameter in a deep learning model in which the signal processing DNN and the classification DNN are fused.

公开(公告)号：US09805716B2

公开(公告)日：2017-10-31

申请号：US15042309

申请日：2016-02-12

Applicant: Electronics and Telecommunications Research Institute

Inventor： Sung Joo Lee ,  Byung Ok Kang ,  Jeon Gue Park ,  Yun Keun Lee ,  Hoon Chung

IPC: G10L15/14 ,  G10L15/16 ,  G10L15/06 ,  G10L21/02

CPC classification number: G10L15/142 ,  G10L15/063 ,  G10L15/16 ,  G10L21/02

Abstract: Provided is an apparatus for large vocabulary continuous speech recognition (LVCSR) based on a context-dependent deep neural network hidden Markov model (CD-DNN-HMM) algorithm. The apparatus may include an extractor configured to extract acoustic model-state level information corresponding to an input speech signal from a training data model set using at least one of a first feature vector based on a gammatone filterbank signal analysis algorithm and a second feature vector based on a bottleneck algorithm, and a speech recognizer configured to provide a result of recognizing the input speech signal based on the extracted acoustic model-state level information.