• Proceedings of the Acoustical Society of Korea Conference
• /
• 한국음향학회 2002년도 하계학술발표대회 논문집 제21권 1호
• /
• pp.163-166
• /
• 2002

본 논문에서는 ETRI 방송 뉴스 자막 처리 시스템의 성능 향상을 도모하기 위해 개발된 미등록어 검출기에 대해 기술한다. 음성 인식 성능 하락에 큰 영향을 미치는 요인들 중 하나로 꼽히는 미등록어 문제를 해결하기 위해 ETRI 방송 뉴스 자막 처리 시스템에서는 오프라인으로 동작하는 미등록어 검출기를 채택하였다. 이 미등록어 검출기는 방송 뉴스 자막 처리 시스템 가동 전에 미리 인터넷을 통해 최신 신문 기사와 방송 뉴스를 수집해와 이를 토대로 두 단계에 걸쳐 미등록어를 사전에 추출하여 인식 어휘 사전에 포함시킴으로써 미등록어로 인한 방송 뉴스의 인식 성능 저하 문제를 해결하도록 하였다.

• Culinary science and hospitality research
• /
• 제15권2호
• /
• pp.93-107
• /
• 2009

The aims of this study concerning tourists travelling in the island of Jeju include: to identify and assess the promotional efforts for traditional Jeju cuisine; and to identify the impacts of those efforts on customers and tourists. The analyses revealed that continuous promotion efforts, along with changes in the cooking methods and the development of new menus, are needed for the items of traditional Jeju cuisine that are relatively unknown to tourists and that fail to satisfy customers. Customers seeking Jeju food reported high satisfaction with such items as grilled meat and fish, steamed meat and fish, and raw fish(hoe), so those cooking methods must also be continually improved. Promotional efforts had impacts on the satisfaction and revisit rates of customers while the recognizability of foods offered had impacts on all areas, including the satisfaction and revisit rates of customers as well as word-of-mouth advertising among them. There needs to be an experience-oriented or educational program that introduces customers to traditional Jeju cuisine. Since customers and tourists gain information on traditional Jeju cuisine from the recommendations and word-of-mouth advertising from the locals they meet on the island, traditional Jeju cuisine should also be advertised to the local residents. The commercial merchandising of Jeju culinary culture and making festivals based on it must, therefore, be preceded by studies on how to increase the locals' awareness of local traditional cuisine.

• Journal of the Institute of Electronics and Information Engineers
• /
• 제50권11호
• /
• pp.153-161
• /
• 2013

Recently, there has been a tremendous increase in the availability of educational materials for foreign language learning. As part of this trend, there has been an increase in the amount of electronically mediated materials available. However, conventional educational contents developed using computer technology has provided typically one-way information, which is not the most helpful thing for users. Providing the user's convenience requires additional off-line analysis for diagnosing an individual user's learning. To improve the user's comprehension of texts written in a foreign language, we propose an intelligent learning tool based on the analysis of the user's eyeball movements, which is able to diagnose and improve foreign language reading ability by providing necessary supplementary aid just when it is needed. To determine the user's learning state, we correlate their eye movements with findings from research in cognitive psychology and neurophysiology. Based on this, the learning tool can distinguish whether users know or do not know words when they are reading foreign language sentences. If the learning tool judges a word to be unknown, it immediately provides the student with the meaning of the word by extracting it from an on-line dictionary. The proposed model provides a tool which empowers independent learning and makes access to the meanings of unknown words automatic. In this way, it can enhance a user's reading achievement as well as satisfaction with text comprehension in a foreign language.

• The Journal of the Acoustical Society of Korea
• /
• 제10권4호
• /
• pp.27-37
• /
• 1991

This paper proposes the ESFVQ(energy subspace fuzzy vector quantization) that employs energy subspaces to reduce the quantizing distortion which is less than that of a fuzzy vector quatization. The ESFVQ is applied to a speaker adaptation method by which Korean words spoken by unknown speakers are recognized. By generating mapped codebooks with fuzzy histogram according to each energy subspace in the training procedure and by decoding a spoken word through the ESFVQ in the recognition proecedure, we attempt to improve the recognition rate. The performance of the ESFVQ is evaluated by measuring the quantizing distortion and the speaker adaptive recognition rate for DDD telephone area names uttered by 2 males and 1 female. The quatizing distortion of the ESFVQ is reduced by 22% than that of a vector quantization and by 5% than that of a fuzzy vector quantization, and the speaker adaptive recognition rate of the ESFVQ is increased by 26% than that without a speaker adaptation and by 11% than that of a vector quantization.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• 제20권3호
• /
• pp.43-48
• /
• 2019

While reading text-only documents and finding unknown words, readers will become the focus disturbed and not be able to understand the content of the documents. Because children have little experience, it is difficult to understand correctly if the description in context is unfamiliar or ambiguous. In this paper, in order to help understand the text and increase the interest of the readers, we analyze the texts of documents and select the contents that are considered important, and implement a system that displays the most relevant images automatically from the web and links the texts and the images together. The implementation of the system divides the article into paragraphs, analyzes the text, selects important sentences for each paragraph and the important words that best represent the meaning of the important sentences, searches for images related to the words on the web, and then links the images to each of the previous paragraphs. Experiments have shown how to select important sentences and how to select important words in the sentences. As a result of the experiment, we could get 60% performance by evaluating the accuracy of the relation between three selected images and corresponding important sentences.

• Journal of Sasang Constitutional Medicine
• /
• 제31권1호
• /
• pp.65-78
• /
• 2019

Objectives This study aims to investigate how the Korean disease-related vocabulary is established or changed when it is translated into French or English. Through this, we examine changes in the meaning of diseases and the ecosystem of disease-related vocabulary in transition period of $19^{th}$ to $20^{th}$ century. Methods Korean disease-related vocabulary are extracted from a total of 148,000 Korean headwords included in our corpus of three bilingual dictionaries. Among them, the scope of analyisis is limited to group of vocabularies that include a high frequency words, disease(病) and symptom(症). Results The first type of change is the emergence of a neologism. In this case, coexistence of existing vocabulary and new words is observed. The second change is the appearance of loan words written in Hangul. The third is the case where the interpretation of meaning is changed while maintaining the word form. Finally, the fourth change is that the orthographic variants are displayed while maintaining the meaning of the existing vocabulary. Discussion Disease-related vocabulary increased greatly between 1897 and 1931. The increasing factor of vocabulary was the emergence of coined words, compound words and the influx of foreign words. The Korean language and the Western language made a new lexical form in order to introduce a new unknown concept to the Korean. We could also confirm that the way in which English word expanded its semantic field by modifying the way of representing the meaning of Korean Disease-related vocabulary.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• 제27권3호
• /
• pp.563-577
• /
• 2017

Due to the Internet and computing capability, new and variant malware are discovered around 1 Million per day. Companies use dynamic analysis such as behavior analysis on virtual machines for unknown malware detection because attackers use unknown malware which is not detected by signature based AV effectively. But growing number of malware types are not only PE(Portable Executable) but also non-PE such as MS word or PDF therefore dynamic analysis must need more resources and computing powers to improve detection effectiveness. This study elicits the pre-filtering system evaluation factor to improve effective dynamic malware analysis system and presents and verifies the decision making model and the formula for solution selection using AHP(Analytics Hierarchy Process)

• Korean Journal of Cognitive Science
• /
• 제4권1호
• /
• pp.177-212
• /
• 1993

My research is based on the parser for ill-formed input by Mellish in a paper in ACL 27th meeting Proceedings. 1989. My system is composed of two parsers:WFCP and IFCP. When WFCP fails to give the parse tree for the input sentence, the sentence is identified as ill-formed and is parsed by IFCP for error detection and recovery at the syntactic level. My system is indendent of grammatical rules. It does not take into account semantic ill-formedness. My system uses a grammar composed of 25 context-free rules. My system consistes of two major parsing strategies:top-down expection and bottem-up satisfaction. With top-down expectation. rules are retrieved under the inference condition and expaned by inactive arcs. When doing bottom-up parsing. my parser used two modes:Left-Right parsing and Right-to-Left parsing. My system repairs errors sucessfully when the input contains an omitted word or an unknown word substitued for a valid word. Left- corner and right-corner errors are more easily detected and repaired than ill-formed senteces where the error is in teh middle. The deviance note. with repair details, is kept in new inactive arcs which are generated by the error correction procedure. The implementation of my system is quite different from Mellish's. When rules are invoked. my system invokes all rules with minimal inference. My bottom up parsing strategy uses Left-to-Right mode and Right-to-Left mode. My system is bottom-up-parsing-oriented like the chart parser. Errors are repaired in two ways:using top-down hypothesis, and using Need-Chart which keeps the information of expectation and complection of expanded goals by rules. To reduce the number of top-down cycles. all rules are invoked simultaneously and this invocation information is kept in Need-Chart. This idea will be extended for the implementation of multiple error recovery system.

• Journal of the Institute of Convergence Signal Processing
• /
• 제2권4호
• /
• pp.9-15
• /
• 2001

In this paper we investigate context dependent acoustic models to improve the performance of the Korean speech recognition . The algorithm are using the Korean phonological rules and decision tree, By Successive State Splitting(SSS) algorithm the Hidden Merkov Netwwork(HM-Net) which is an efficient representation of phoneme-context-dependent HMMs, can be generated automatically SSS is powerful technique to design topologies of tied-state HMMs but it doesn't treat unknown contexts in the training phoneme contexts environment adequately In addition it has some problem in the procedure of the contextual domain. In this paper we adopt a new state-clustering algorithm of SSS, called Phonetic Decision Tree-based SSS (PDT-SSS) which includes contexts splits based on the Korean phonological rules. This method combines advantages of both the decision tree clustering and SSS, and can generated highly accurate HM-Net that can express any contexts To verify the effectiveness of the adopted methods. the experiments are carried out using KLE 452 word database and YNU 200 sentence database. Through the Korean phoneme word and sentence recognition experiments. we proved that the new state-clustering algorithm produce better phoneme, word and continuous speech recognition accuracy than the conventional HMMs.

• Journal of the Korean Society of Food Culture
• /
• 제30권2호
• /
• pp.137-149
• /
• 2015

This study explores the original text of a Korean recipe book written in the 17th century, which is hitherto unknown to food-related societies, and analyzes the characteristics of the recipes in this book. Choi's recipes in Jasonbojoen (子孫寶傳) are significant, as it is a rare instance of a Korean cookbook written by a woman-few pre-17th century recipe books of this type are known to have survived. This study made some important discoveries after analyzing this book. First, by using pasqueflower and cockscomb, it was possible to identify the era-specific characteristics of kimchi recipes from the 1400s until after the 1700s. Second, this book has historical value, as it shows that the combination of kimchi with cockscomb and the recipe for stuffed eggplant kimchi made only with a small portion of garlic and salt have existed for longer than was previously believed. Third, this book can serve as a valuable database for studies on historical changes in Korean food recipes, as the recipes in this book besides those related to kimchi are representative of recipes in cookbooks before the 17th century. Additionally, it appears that some recipes in the book use very unique minor ingredients that cannot be found in other books.