公开(公告)号：US20170133006A1

公开(公告)日：2017-05-11

申请号：US15344110

申请日：2016-11-04

Applicant: Samsung Electronics Co., Ltd.

Inventor： Ho Shik LEE ,  Hee Youl CHOI

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

Abstract: A neural network training apparatus includes a primary trainer configured to perform a primary training of a neural network model based on clean training data and target data corresponding to the clean training data; and a secondary trainer configured to perform a secondary training of the neural network model on which the primary training has been performed based on noisy training data and an output probability distribution of an output class for the clean training data calculated during the primary training of the neural network model.

公开(公告)号：US20170148430A1

公开(公告)日：2017-05-25

申请号：US15332166

申请日：2016-10-24

Applicant: Samsung Electronics Co., Ltd.

Inventor： Ho Shik LEE

IPC: G10L15/06 ,  G10L15/01 ,  G10L15/16

CPC classification number: G10L15/063 ,  G10L15/01 ,  G10L15/16 ,  G10L2015/0635

Abstract: A method and a device for recognition, and a method and a device for constructing a recognition model are disclosed. A device for constructing a recognition model includes a training data inputter configured to receive additional training data, a model learner configured to train a first recognition model constructed based on basic training data to learn the additional training data, and a model constructor configured to construct a final recognition model by integrating the first recognition model with a second recognition model generated by the training of the first recognition model.