• Journal of the Korea Computer Graphics Society
• /
• v.26 no.3
• /
• pp.49-59
• /
• 2020

In this paper, we propose a speech animation synthesis specialized in Korean through a rule-based co-articulation model. Speech animation has been widely used in the cultural industry, such as movies, animations, and games that require natural and realistic motion. Because the technique for audio driven speech animation has been mainly developed for English, however, the animation results for domestic content are often visually very unnatural. For example, dubbing of a voice actor is played with no mouth motion at all or with an unsynchronized looping of simple mouth shapes at best. Although there are language-independent speech animation models, which are not specialized in Korean, they are yet to ensure the quality to be utilized in a domestic content production. Therefore, we propose a natural speech animation synthesis method that reflects the linguistic characteristics of Korean driven by an input audio and text. Reflecting the features that vowels mostly determine the mouth shape in Korean, a coarticulation model separating lips and the tongue has been defined to solve the previous problem of lip distortion and occasional missing of some phoneme characteristics. Our model also reflects the differences in prosodic features for improved dynamics in speech animation. Through user studies, we verify that the proposed model can synthesize natural speech animation.

• Journal of The Korean Association For Science Education
• /
• v.34 no.4
• /
• pp.359-366
• /
• 2014

In this study, we try to examine its features by using the methods of systematic infographics analysis for visualization materials that are used in Physics I textbooks. Thus, after developing the analytical framework infographics, visualization materials is described in the section "information and communication" and have been analyzed separately as "data visualization" and "Infographics." The results of this study are as follows. First, the analysis framework of infographics can be classified contents of the information, visual representation, and media method. Second, the visualization materials that are displayed in the section "information and communication" of Physics I textbook are of higher quality than most schematized data that are graphically, simple information. Third, the features of visualization materials in textbooks have many relations & functions on 'information content', text & metaphor on 'visual element', illustration & comparison on 'expression type', graphic on 'expression mode', printed matter on 'media method', and horizontal & vertical type on 'the flow of attention'. From the analysis results, in the section "information and communication" of Physics I textbook uses a lot of visualization materials, however it does not provide rich infographics but only simple graphical materials. By utilizing the results of the analysis of textbook and analysis framework of infographics, which has been developed through the this study, let us hope that the opportunity to be able to grasp the importance of infographics in science education be provided.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.7
• /
• pp.335-347
• /
• 2024

Open-vocabulary 3D point cloud instance segmentation (OV-3DIS) is a challenging visual task to segment a 3D scene point cloud into object instances of both base and novel classes. In this paper, we propose a novel model Open3DME for OV-3DIS to address important design issues and overcome limitations of the existing approaches. First, in order to improve the quality of class-agnostic 3D masks, our model makes use of T3DIS, an advanced Transformer-based 3D point cloud instance segmentation model, as mask proposal module. Second, in order to obtain semantically text-aligned visual features of each point cloud segment, our model extracts both 2D and 3D features from the point cloud and the corresponding multi-view RGB images by using pretrained CLIP and OpenSeg encoders respectively. Last, to effectively make use of both 2D and 3D visual features of each point cloud segment during label assignment, our model adopts a unique feature ensemble method. To validate our model, we conducted both quantitative and qualitative experiments on ScanNet-V2 benchmark dataset, demonstrating significant performance gains.

• Journal of Intelligence and Information Systems
• /
• v.25 no.3
• /
• pp.201-220
• /
• 2019

Fake news has emerged as a significant issue over the last few years, igniting discussions and research on how to solve this problem. In particular, studies on automated fact-checking and fake news detection using artificial intelligence and text analysis techniques have drawn attention. Fake news detection research entails a form of document classification; thus, document classification techniques have been widely used in this type of research. However, document summarization techniques have been inconspicuous in this field. At the same time, automatic news summarization services have become popular, and a recent study found that the use of news summarized through abstractive summarization has strengthened the predictive performance of fake news detection models. Therefore, the need to study the integration of document summarization technology in the domestic news data environment has become evident. In order to examine the effect of extractive summarization on the fake news detection model, we first summarized news articles through extractive summarization. Second, we created a summarized news-based detection model. Finally, we compared our model with the full-text-based detection model. The study found that BPN(Back Propagation Neural Network) and SVM(Support Vector Machine) did not exhibit a large difference in performance; however, for DT(Decision Tree), the full-text-based model demonstrated a somewhat better performance. In the case of LR(Logistic Regression), our model exhibited the superior performance. Nonetheless, the results did not show a statistically significant difference between our model and the full-text-based model. Therefore, when the summary is applied, at least the core information of the fake news is preserved, and the LR-based model can confirm the possibility of performance improvement. This study features an experimental application of extractive summarization in fake news detection research by employing various machine-learning algorithms. The study's limitations are, essentially, the relatively small amount of data and the lack of comparison between various summarization technologies. Therefore, an in-depth analysis that applies various analytical techniques to a larger data volume would be helpful in the future.

• The Journal of the Korea Contents Association
• /
• v.14 no.11
• /
• pp.79-88
• /
• 2014

Vampilov, who is not well known as a playwright in domestic, is acknowledged comparable to Anton Chekhov in Russia. This paper was planed in order to promote a unsatisfied study until now in domestic for works by Vampilov and studied a part of composing play to put on the stage for , a drama written by Vampilov. This paper, originated from a viewpoint that actor have to complete the final text of the play for audiences to read depending on the drama and based on work features and characters of Vampilov, established an analysis scheme according to segments of unit actions for actions of Sarafanov, the character of the play, in order to achieve a purpose under suggested situation at the drama and focused on completing purposes per units individually. We have analyzed Sarafanov and his actions referring patterns and probabilities of the characters in the other works by Vampiov and regarded it as the important item together with logical basis of actions. Lyric and humanism emphasizing works by Vampilov, affected by Anton Chekhov and Nikolai Vasilevich Gogol, are acknowledged as realistic descriptions using contingency and a play within a play outstandingly and emphasized an importance of human relation. We have selected as a primary way to compose action text that audiences would read on the stage and used it as the method to design action of the characters in order to activate natural good of Sarafanov and general absurdities that human, does creative works, never give up purposes of ideal life.

• Journal of Multimedia Information System
• /
• v.5 no.3
• /
• pp.147-154
• /
• 2018

Natural language processing (NLP) is an emerging research area in which we study how machines can be used to perceive and alter the text written in natural languages. We can perform different tasks on natural languages by analyzing them through various annotational tasks like parsing, chunking, part-of-speech tagging and lexical analysis etc. These annotational tasks depend on morphological structure of a particular natural language. The focus of this work is part-of-speech tagging (POS tagging) on Hindi language. Part-of-speech tagging also known as grammatical tagging is a process of assigning different grammatical categories to each word of a given text. These grammatical categories can be noun, verb, time, date, number etc. Hindi is the most widely used and official language of India. It is also among the top five most spoken languages of the world. For English and other languages, a diverse range of POS taggers are available, but these POS taggers can not be applied on the Hindi language as Hindi is one of the most morphologically rich language. Furthermore there is a significant difference between the morphological structures of these languages. Thus in this work, a POS tagger system is presented for the Hindi language. For Hindi POS tagging a hybrid approach is presented in this paper which combines "Probability-based and Rule-based" approaches. For known word tagging a Unigram model of probability class is used, whereas for tagging unknown words various lexical and contextual features are used. Various finite state machine automata are constructed for demonstrating different rules and then regular expressions are used to implement these rules. A tagset is also prepared for this task, which contains 29 standard part-of-speech tags. The tagset also includes two unique tags, i.e., date tag and time tag. These date and time tags support all possible formats. Regular expressions are used to implement all pattern based tags like time, date, number and special symbols. The aim of the presented approach is to increase the correctness of an automatic Hindi POS tagging while bounding the requirement of a large human-made corpus. This hybrid approach uses a probability-based model to increase automatic tagging and a rule-based model to bound the requirement of an already trained corpus. This approach is based on very small labeled training set (around 9,000 words) and yields 96.54% of best precision and 95.08% of average precision. The approach also yields best accuracy of 91.39% and an average accuracy of 88.15%.

• Korean Journal of Cognitive Science
• /
• v.21 no.1
• /
• pp.157-175
• /
• 2010

Understanding dialogue participant's emotion is important as well as decoding the explicit message in human communication. It is well known that non-verbal elements are more suitable for conveying speaker's emotions than verbal elements. Written texts, however, contain a variety of linguistic units that express emotions. This study aims at analyzing components for constructing an emotion ontology, that provides us with numerous applications in Human Language Technology. A majority of the previous work in text-based emotion processing focused on the classification of emotions, the construction of a dictionary describing emotion, and the retrieval of those lexica in texts through keyword spotting and/or syntactic parsing techniques. The retrieved or computed emotions based on that process did not show good results in terms of accuracy. Thus, more sophisticate components analysis is proposed and the linguistic factors are introduced in this study. (1) 5 linguistic types of emotion expressions are differentiated in terms of target (verbal/non-verbal) and the method (expressive/descriptive/iconic). The correlations among them as well as their correlation with the non-verbal expressive type are also determined. This characteristic is expected to guarantees more adaptability to our ontology in multi-modal environments. (2) As emotion-related components, this study proposes 24 emotion types, the 5-scale intensity (-2~+2), and the 3-scale polarity (positive/negative/neutral) which can describe a variety of emotions in more detail and in standardized way. (3) We introduce verbal expression-related components, such as 'experiencer', 'description target', 'description method' and 'linguistic features', which can classify and tag appropriately verbal expressions of emotions. (4) Adopting the linguistic tag sets proposed by ISO and TEI and providing the mapping table between our classification of emotions and Plutchik's, our ontology can be easily employed for multilingual processing.

• Journal of the Korean Society for Marine Environment & Energy
• /
• v.5 no.3
• /
• pp.28-34
• /
• 2002

As the technology of Speech Recognition(SR) and Text-To-Speech(TTS) develops rapidly, voice control and guidance system is thought to be very helpful for safe navigation. But Voice Control and Guidance System(VCGS) is not yet so popularly included in Navigation Supporting System(NSS). The main reason of this is that VCGS is so complicated and user-unfriendly that navigation officers hesitate to use VCGS. Frequent errors in operating VCGS due to low rate of SR are another reason. To make VCGS more practicable for safe navigation, we design the user-friendly VCGS. Firstly, by using interviews we survey functions and procedures that navigation officers want to be included in VCGS. Secondly, to raise the rate of SR, we tun the environmental noise in bridge and to reduce the errors due to low rate of SR in operating VCGS, we design the functions of self-correction. Also we apply a user-independent SR engine so that procedures of teaming of speakers is basically not necessary. Using simulator experiments the functions and procedures of the user-friendly YCGS for safe navigation are evaluated and the results of evaluation are fed back to the design. As a result, we can design the VCGS more helpful for safe navigation. In this paper, we describe the features of the user-friendly VCGS for safe navigation and discuss the results of simulator experiments.

• Korean Journal of Agricultural and Forest Meteorology
• /
• v.19 no.4
• /
• pp.270-279
• /
• 2017

Regional assessment of crop productivity using a gridded simulation approach could aid policy making and crop management. Still, little effort has been made to develop the systems that allows gridded simulations of crop growth using ORYZA 2000 model, which has been used for predicting rice yield in Korea. The objectives of this study were to develop a series of data processing modules for creating input data files, running the crop model, and aggregating output files in a region of interest using gridded data files. These modules were implemented using C++ and R to make the best use of the features provided by these programming languages. In a case study, 13000 input files in a plain text format were prepared using daily gridded weather data that had spatial resolution of 1km and 12.5 km for the period of 2001-2010. Using the text files as inputs to ORYZA2000 model, crop yield simulations were performed for each grid cell using a scenario of crop management practices. After output files were created for grid cells that represent a paddy rice field in South Korea, each output file was aggregated into an output file in the netCDF format. It was found that the spatial pattern of crop yield was relatively similar to actual distribution of yields in Korea, although there were biases of crop yield depending on regions. It seemed that those differences resulted from uncertainties incurred in input data, e.g., transplanting date, cultivar in an area, as well as weather data. Our results indicated that a set of tools developed in this study would be useful for gridded simulation of different crop models. In the further study, it would be worthwhile to take into account compatibility to a modeling interface library for integrated simulation of an agricultural ecosystem.

• The Journal of the Korea Contents Association
• /
• v.21 no.4
• /
• pp.795-814
• /
• 2021

With the development of science and technology in recent years, various types of unstructured buildings have begun to be implemented by combining traditional architectural styles with digital tools, which are significantly different from conventional formal buildings. Designers will use various methods or digital tools to complete the unstructured and freer architectural forms when building an unstructured building. Based on this background, the need for research on the criteria for evaluating the characteristics of unstructured architectural forms is raised. First, the text was reconstructed by considering and integrating the elements of the unstructured exterior form based on prior research, with the external form of the unstructured building as the main research object. Second, the purpose of this study was to classify various types of unstructured forms and to provide important basic data for designing digital processes of unstructured architectural forms.Third, from 2000 to 2020, the text focused on the study of unstructured buildings and conducted in-depth analysis of the characteristics of their form expressions. While providing a case basis for the study of related fields, distribution laws and presence values related to the characteristics of unstructured buildings were sought. In addition, the analysis was conducted in combination with the distribution of functional use of buildings, and this study is differentiated from the existing research in that the atypical form is applied to the buildings by use, and the application trend of this type is understood to enhance understanding of the atypical form of buildings.