• Journal of the Korea Computer Graphics Society
• /
• v.28 no.3
• /
• pp.23-29
• /
• 2022

Virtual humans are implemented with dedicated modeling tools like Unity 3D Engine in virtual space (virtual reality, mixed reality, metaverse, etc.). Various human modeling tools have been introduced to implement virtual human-like appearance, voice, expression, and behavior similar to real people, and virtual humans implemented via these tools can communicate with users to some extent. However, most of the virtual humans so far have stayed unimodal using only text or speech. As AI technologies advance, the outdated machine-centered dialogue system is now changing to a human-centered, natural multi-modal system. By using several pre-trained networks, we implemented an emotion-based multi-modal dialogue system, which generates human-like utterances and displays appropriate facial expressions in real-time.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.179-185
• /
• 2019

A core technology of social robot is voice recognition and dialogue engine technology, but too much money is needed for development and an implementation of robot's conversation function is difficult resulting from insufficiency of performance. Dialogue function's implementation between human and robot can be possible due to advance of cloud AI technology and several company's supply of their open API. In this paper, current intelligent social robot technology trend is investigated and effective social robot system architecture is designed. Also an effective analysis and design method of social robot system will be presented by showing user requirement analysis using object-oriented method, flowchart and screen design.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.620-622
• /
• 2021

With the rise of the game industry, the importance of the game's storytelling is also increasing. Delivering a specific world view of a game has a tremendous effect on the immersion of the game, so the method of delivering a story needs to be studied continuously. In this study, the character was implemented using 3D modelling tool, and the initial story of the game was delivered through a dialogue window using a game engine. Through the research, we were able to establish a workflow for telling stories using a character and understand each process in depth, which we expect to be the basis for more sophisticated game character development and smooth storytelling in the future.

• Journal of Fisheries and Marine Sciences Education
• /
• v.2 no.1
• /
• pp.29-35
• /
• 1989

It is indispensable for the marine officers who are engaged in the international voyage to make command of maritime English fluently. The Marine Officers Act in Korea which is under ammending in 1989 prescribes the proportion of maritime Englishin English examination is made to be 60% for the 4th and 5th class marine officer-license examination. A concrete syllabus or content of maritime English is not established yet with the exception of a general prescription of minimun knowledge required for certification of marine officers in the IMO/STCW Convention. The authors, who rewrote the maritime English textbook for the course of the fisheries high, schools and the merchant marine high schools, settled the syllabi of nautical English and marine engineering English for the course as follows : 1. The syllabus of nautical English, includes maritime English readings, the IMO English dialogue on port entry, writing of logbooks, night order books, and docking and repair specifications. 2. The syllabus of marine engineering English includes maritime English readings, dialogue on oil supply, writing of engine logbooks and oil record books, standing orders, and docking and repair specifications. The authors propose that the realm of these class marine officer-license examination on maritime English should be limited within in the above mentioned textbook. As maritime English is made to be included in the 4th and 5th marine officer liscence examination since 1989, high schools concerned need to reform the curricula to complete at least 6 units for this subject. On the other hand, the competent authority of this examination must secure questions as much as possible to promote the reliability of them.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.7
• /
• pp.847-856
• /
• 2017

In this paper, we propose a system to users which recommends suitable park using linguistic objects by rule-based inference engine which is made with Prolog. According to the function of city park, which provides positive elements to people such as social, psychological, environmental, and physical, Seoul city park is classified into 6 categories. The classified parks are recommended to users based on the rule based expert system. Rule-based object of park recommendation designs nine linguistic objects based on activity, multi-purposiveness, accessibility, and usage of time. This assigns allowed value accordingly. Generated rules by using these values are fired by user's preference, and infer recommended park. Information on preferences is obtained by way of dialogue, in which the user is asked questions about the three elements that are the criteria for choosing a park. As a result, through the park recommendation system, we intend to increase the user's satisfaction of using park and leisure activities.

• Journal of the Korea Computer Graphics Society
• /
• v.29 no.3
• /
• pp.21-31
• /
• 2023

In this paper, we introduce a case study of cinematography using digital human in virtual production. This case study deals with the system overview of virtual production using LEDs and an efficient filming pipeline using digital human. Unlike virtual production using LEDs, which mainly project the background on LEDs, in this case, we use digital human as a virtual actor to film scenes communicating with a real actor. In addition, to film the dialogue scene between the real actor and the digital human using a real-time engine, we automatically generated speech animation of the digital human in advance by applying our Korean lip-sync technology based on audio and text. We verified this filming case by using a real-time engine to produce short drama content using real actor and digital human in an LED-based virtual production environment.

• Journal of Semiconductor Engineering
• /
• v.2 no.2
• /
• pp.130-135
• /
• 2021

Recently, deep neural networks (DNNs) are actively used for action control so that an autonomous system, such as the robot, can perform human-like behaviors and operations. Unlike recognition tasks, the real-time operation is essential in action control, and it is too slow to use remote learning on a server communicating through a network. New learning techniques, such as reinforcement learning (RL), are needed to determine and select the correct robot behavior locally. In this paper, we propose an energy-efficient DNN processor with a LUT-based processing engine and near-zero skipper. A CNN-based facial emotion recognition and an RNN-based emotional dialogue generation model is integrated for natural HRI system and tested with the proposed processor. It supports 1b to 16b variable weight bit precision with and 57.6% and 28.5% lower energy consumption than conventional MAC arithmetic units for 1b and 16b weight precision. Also, the near-zero skipper reduces 36% of MAC operation and consumes 28% lower energy consumption for facial emotion recognition tasks. Implemented in 65nm CMOS process, the proposed processor occupies 1784×1784 um2 areas and dissipates 0.28 mW and 34.4 mW at 1fps and 30fps facial emotion recognition tasks.

• Journal of KIISE:Computing Practices and Letters
• /
• v.11 no.2
• /
• pp.101-111
• /
• 2005

The present web informations are mainly described in terms of HTML, which users obtain through input devices such as mouse, keyboard, etc. Thus the existing GUI environment have not supported human's most natural information acquisition means, that is, voice. To solve the problem, several vendors are developing voice user interface. However these products are deficient in man -machine interactivity and their accommodation of existing web environment. This paper presents a VUI(Voice User Interface) supporting web browser by utilizing more and more maturing speech recognition technology and VoiceXML, a markup language derived from XML. It provides users with both interfaces, VUI as well as GUI. In addition, XML Island technology is applied to the bowser in a way that VoiceXML fragments are nested in HTML documents to accommodate the existing web environment. Also for better interactivity, dialogue scenarios for menu, bulletin, and search engine are suggested.