• Speech Sciences
• /
• v.3
• /
• pp.119-131
• /
• 1998

We have developed a keyword spotting system for automatic speech editing. This system recognizes the only keyword 'MBC news' and then sends the time information to the host system. We adopted a vocabulary dependent model based on continuous hidden Markov model, and the Viterbi search was used for recognizing the keyword. In recognizing the keyword, the system uses a parallel network where HMM models are connected independently and back-tracking information for reducing false alarms and missing. We especially focused on implementing a stable and practical real-time system.

• Journal of the Korea Society of Computer and Information
• /
• v.22 no.2
• /
• pp.65-73
• /
• 2017

The objective of this study is to suggest the templates for the terminology standardization cases of safety standard on integrated management system, so that integrated management of safety standards is introduced to replace redundant, or conflicting functions and performance of these standards. And to carry out the terminology standardization enables management efficiently. Therefore this study suggests and analyzes cases of terminology standardization of domestic and international research trends. In addition to proposes a architectural schema for disaster safety standard and writing disaster safety standardizations of the International Organization for Standardization. For the objectives, the guidelines on standard terminology policy, terminology publication and guide development proposed by the International Organization for Standardization. Disaster safety standards were applied in order to build and utilize integrated management system of disaster safety standards through domestic and foreign cases. Throughout the result of this study, this study will contribute to the analysis and application of semantic knowledge based analysis throughout the ontology information linked the vocabulary to vocabulary by making the template of the disaster safety standards for easy to use and simple etc. This study is to expect traceability for the principle national disaster safety standards resource elements.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.8
• /
• pp.3-8
• /
• 1999

Previous variable vocabulary speech recognition systems with context-independent acoustic modeling, could not represent the effect of neighboring phonemes. To solve this problem, we use allophone-based context-dependent acoustic model. This paper describes the method to improve acoustic model of the system effectively. Acoustic model is improved by using allophone clustering technique that uses entropy as a similarity measure and the optimal allophone model is generated by changing the number of allophones. We evaluate performance of the improved system by using Phonetically Optimized Words(POW) DB and PC commands(PC) DB. As a result, the allophone model composed of six hundreds allophones improved the recognition rate by 13% from the original context independent model m POW test DB.

• MALSORI
• /
• no.50
• /
• pp.123-137
• /
• 2004

In this paper, we consider the implementation of connected digit recognition system using tree structured lexicon model. To implement efficiently the fixed or variable length digit recognition system, finite state network (FSN) is required. We merge the word network algorithm that implements the FSN with lexical tree search algorithm that is used for general speech recognition system for fast search and large vocabulary systems. To find the efficient modeling of digit recognition system, we investigate some performance changes when the lexical tree search is applied.

• Phonetics and Speech Sciences
• /
• v.1 no.2
• /
• pp.3-8
• /
• 2009

In an effort to improve speech recognition, we investigated the effect of the number of clusters. In usual LBG clustering, the number of codebook clusters is doubled on each bifurcation and hence cannot be chosen arbitrarily in a natural way. To have the number of clusters at our control, we combined adaptive resonance theory (ART2) with LBG and perform the clustering in two stages. The codebook thus formed was used in subsequent processing of fuzzy vector quantization (FVQ) and HMM for speech recognition tests. Compared to conventional LBG, our method was shown to reduce the best recognition error rate by 0${\sim$}0.9% depending on the vocabulary size. The result also showed that between 400 and 800 would be the optimal number of clusters in the limit of small and large vocabulary speech recognitions of isolated words, respectively.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10c
• /
• pp.559-561
• /
• 2003

최근 차세대 Web 기술로서 Semantic Web이 주목 받고 있다. Semantic Web에서는 Web상에 존재하는 문서에 Web Resource들에 대한 Ontology를 기반으로 Semantic Annotation을 하고 Ontology 추론 Agent를 통하여 의미 기반으로 Web을 검색할 수 있도록 해준다. 이와 같은 Semantic Web 기술의 핵심 요소는 Web Ontology이며 W3C에서는 이를 표현 할 수 있는 표준 언어로서 RDF기반의 OWL(Web Ontology Language) 명세를 제정하고 있다. 따라서 표준 Web Ontology 언어인 OWL을 위한 추론 시스템은 Semantic Web 검색 Agent의 구현을 위한 필수적인 기반 기술이라 할 수 있으나 아직 그 개발이 미비한 상태이다. OWL 추론 시스템을 구현하기 위해서는 OWL의 이론적인 기반을 제공하는 DL(Description Logic)을 추론할 수 있는 엔진을 사용하는 것이 한가지 방법이 될 수 있으나 OWL이 Rule과 같은 DL의 범주를 벗어나는 Vocabulary를 지원하는 언어로 확장되는 경우에 이를 처리하기가 어렵다. 또 다른 방법으로서 Logic Programming을 통하여 OWL 언어의 Semantic을 기술하고 정리 증명(Theorem Proving)을 통하여 Ontology를 추론하는 공리화(Axiomatisation) 기법이 있는데 이러한 방법의 장점은 기반이 되는 Logic의 범주 내에서 새로운 언어를 위한 Vocabulary의 확장이 용이하다는 점이다. 본 논문에서는 Axiomatisation 방법을 이용하여 OWL로 기술된 Ontology를 추론할 수 있는 시스템의 설계 및 구현에 대해 설명하기로 한다.

• Proceedings of the Korean Institute of Interior Design Conference
• /
• 2003.05a
• /
• pp.112-116
• /
• 2003

The aim of this study is to extract the design vocabulary of flexibility from analyzing Steven Holl' architectural works. For this purpose, the four works were selected and the design elements like their concepts, elevations, plans, furnitures, lights, materials, and colors were analyzed. The results of this study are as follows ; First, flexible design method is shown in adaptable space planning by using system of hinged panel and multi-functional furniture of various form. Second, Windows were made a plan of the geometric partition of surface and with clear materials for expanding space to outside. Third, the changing of level and the using of the phenomenological elements like a light color, water, and materials were applied for enhancing the image of the flexible space.

• English Language & Literature Teaching
• /
• v.11 no.3
• /
• pp.1-23
• /
• 2005

This paper is a qualitative and quantitative study. The main purpose of the paper is to diagnose what makes English communication difficult at the Korean EFL adult level. In order to obtain data, this study employed interviews and a questionnaire. We identified thirty three factors blocking pathways to oral communication. Qualitative analysis repeatedly revealed patterns such as lack of grammar, lack of vocabulary, lack of background knowledge, and peer pressure, but quantitative analysis yielded somewhat different results: lack of colloquial expressions, lack of vocabulary, lack of various topics, problems in the educational system, difficulty in using existing knowledge, and lack of grammar. Findings which were common to both qualitative and quantitative analyses suggest that lack of linguistic knowledge and lack of background knowledge are major barriers learners encounter in communication. On the basis of the results, suggestions are made for overcoming these barriers.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.56-59
• /
• 1998

POW 3848 DB 및 SNR 이 크게 다른 2 종류의 PC168 DB를 대상으로 가변어휘 음성인식 시스템을 이용하여 훈련 및 성능 평가 실험을 수행한 내용에 대해서 기술하고 있다. 실험의 목적은 위의 3종류의 DB를 조합하여 얻은 DB 환경하에서 인식기를 훈련시키면서, DB 의 조합 및 훈련방법에 따른 인식기의 성능과의 상관관계를 도출하고자 하였다. DB 의 조합은 POW DB 와 SNR 이 높은 PC DB , 및 3종류의 DB 모두로 구성하였다. 인식기는 40개의 음소로 구성된 문맥 독립형 SCHMM 모델이며, 각 음소당 3개의 상태로 이루어져 있다. 실험 결과, 대부분의 경우에서 ITERATION이 1.0인 경우에 최고 인식률을 나타내고 있으며, INTERATION 이 3.0 이상인 경우에는 항상 CASE 3의 실험방법이 우세한 결과를 나타내었다. 또한 CASE 1으로 훈련한 경우가 CASE 2 보다는 각각의 실험 DB 에 대해서 대체적으로 좋은 결과를 보였다.

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.4E
• /
• pp.11-16
• /
• 1998

For large vocabulary speech recognition using HMMs, context-dependent subword units have been often employed. However, when context-dependent phone models are used, they result in a system which has too may parameters to train. The problem of too many parameters and too little training data is absolutely crucial in the design of a statistical speech recognizer. Furthermore, when building large vocabulary speech recognition systems, unseen triphone problem is unavoidable. In this paper, we propose the modified phonetic decision tree algorithm for the automatic prediction of unseen triphones which has advantages solving these problems through following two experiments in Japanese contexts. The baseline experimental results show that the modified tree based clustering algorithm is effective for clustering and reducing the number of states without any degradation in performance. The task experimental results show that our proposed algorithm also has the advantage of providing a automatic prediction of unseen triphones.