Samsung Electronics Co., Ltd.

Hyperconnect Inc.

Imperial Innovations Limited

Myongji University Industry and Academia Cooperation Foundation

Imperial College London

Seung Ju Han

Joon Ah Park

Jae Joon Han

Hyun Jeong Lee

Soo Chul Lim

Do Kyoon Kim

Won Chul Bang

Hyung Kew Lee

Bho Ram Lee

Chang Kyu Choi

Byung In Yoo

Du Sik Park

Wook Chang

Joonah Park

Jung Bae Kim

Seok Jun Seo

Beom Su Kim

Enkhbayar Erdenee

Hyun Surk Ryu

Bu Ru Chang

Ki Myung Lee

Sang Bum Kim

Sang Il Ahn

Tae Kyun Kim

Won Bae Bang

Hyun Yeul Lee

Du-Sik Park

Jong Jin Park

Dong Young Kim

Seon Min Rhee

Seung Woo Choi

Won Jun Hwang

Chi Youn Park

Bhoram Lee

Hyung Jin Chang

Jin Yong Yoo

Danhang Tang

Alykhan Tejani

Sang Kyun Kim

Sung Joo Ha

Kyung Won Moon

Jeong Hwan Ahn

Young Kyoo Hwang

Chang Kyo Lee

Yeon Woo Lee

Kyung-Won Moon

Su Hyun Lee

Se Yeon Oh

Sun Young Bae

Young Jun Kwak

Hyun Suk Ryu

A training method of a conversation model according to various example embodiments of the present disclosure may include identifying a first context, identifying a first response set corresponding to the first context based on a first model, identifying a response subset selected from the first response set based on a gold response corresponding to the first context and training a second model based on the first context information and the response subset.

Method of generating conversation information using examplar-based generation model and apparatus for the same

Disclosed is a method of training a dialogue model in an electronic device, the method including selecting a first context from a first dialogue data set including at least one pair of a context and a response corresponding to the context, generating a first response corresponding to the first context through a first dialogue model, generating an augmented dialogue dataset by incorporating a pair of the first context and the first response corresponding to the first context into the first dialogue data set, and training a second dialogue model based on the augmented dialogue dataset.

Dialogue model training method and device therefor

Systems and techniques to generate imitative responses are illustrated. response generation method performed in an electronic apparatus of the present disclosure includes acquiring at least one piece of utterance data, acquiring a first context corresponding to the utterance data from a context candidate set, generating one or more dialogue sets including the first context and the utterance data, receiving a second context from a user, and acquiring a response corresponding to the second context using a language model based on the one or more dialogue sets.

Method of generating response using utterance and apparatus therefor

Disclosed is a speech synthesis method including acquiring second speech data and a target text, acquiring first information includes embedding information corresponding to the second speech data, acquiring second information including embedding information of the second speech data, the embedding information in relation with components generated based on a sequence of the target text, and acquiring audio data corresponding to the target text and reflecting characteristics of speech of a speaker based on the first information and the second information.

Speech synthesis apparatus and method thereof

Display screen or portion thereof with graphical user interface

An interfacing apparatus may sense an input object and move at least one interface object displayed on a display toward the sensed input object.

Apparatus and method for recognizing proximity motion using sensors

A method to reduce a neural network includes: adding a reduced layer, which is reduced from a layer in the neural network, to the neural network; computing a layer loss and a result loss with respect to the reduced layer based on the layer and the reduced layer; and determining a parameter of the reduced layer based on the layer loss and the result loss.

Method and apparatus to reduce neural network

A content recommendation method and device for recommending content to a user are disclosed. According to one embodiment, the content recommendation device extracts the features of a user from image data, audio data and the like, and can determine a recognition rate indicating the degree that is recognized as a user model predetermined according to the features of the user. The content recommendation device can determine the recommended content to be provided to the user on the basis of the determined recognition rate.

Content recommendation method and device

A device and a method for providing tactile sensation by using electrostatic force between an electrode and a user. The device for providing tactile sensation includes a plurality of electrodes arranged on a substrate, and a dielectric substance layer formed on the substrate and the electrodes, wherein the electrodes electrify the dielectric substance layer with an electric charge according to a driving voltage, so as to generate electrostatic force that provides tactile stimuli to a user who comes into contact with the dielectric substance layer.

Device and method for providing tactile sensation

An apparatus for recognizing a proximity motion using sensors may include a first sensor to sense a first input region, a second sensor to sense a second input region distinct from the first input region, and an information transfer controller to transfer information related to a transition, between the first sensor and the second sensor.

A variable stiffness film, a variable stiffness flexible display, and a manufacturing method thereof may include a lower electrode, a variable fluid, and an upper electrode. A polymer layer may be formed on the lower electrode, and a variable fluid receiving portion is patterned on the polymer layer. A variable stiffness layer is formed by putting a variable fluid in the variable fluid receiving portion. The upper electrode is formed on the variable fluid layer.

Variable stiffness film, variable stiffness flexible display, and method of manufacturing the variable stiffness film

An interfacing device for providing a user interface (UI) exploiting a multi-modality may recognize at least two modality inputs for controlling a scene, and generate scene control information based on the at least two modality inputs.

Interfacing device and method for providing user interface exploiting multi-modality

A virtual world processing apparatus and method. Sensed information, which is information collected by a sensor is inputted. The sensed information is adapted, based on a sensor capability, which is information on capability of the sensor. Accordingly, interoperability between a real world and a virtual world or interoperability between virtual worlds may be achieved.

Virtual world processing device and method

In an apparatus and method for processing a virtual world, haptic information regarding a virtual object in the virtual world, the haptic information corresponding to sensed information, is extracted and transmitted to a haptic feedback device. Accordingly, interaction between a real world and the virtual world is achieved. The processing speed of the haptic information with respect to the virtual object may be increased by varying data structures according to types of the virtual object.

Method and apparatus for processing virtual world

Growing community of inventors

Seoul, South Korea

Seung Ju Han