• The Journal of the Acoustical Society of Korea
• /
• v.10 no.6
• /
• pp.64-70
• /
• 1991

본논문에서는 Hidden Markov Model 에 기초한 실시간 고립 단어 인식 시스템에서의 Viterbi 알 고리듬을 위한 전용 VLSI 구조를 제안하였다. 제안된 구조는 듀얼포트 레지스터 파일로 입출력 부하를 줄이고 가산-최소/최대 연산부의 병렬 연산 구조를 이용하여 실시간 동작이 가능하도록 설계되었다. 모 델 인자와 상태 변수의 값에 태그들을 덧붙임으로써 이 구조는 대표적인 HMM 구조들을 쉽게 구현할 수 있다.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.2
• /
• pp.27-34
• /
• 2001

Utterance verification is used in variable vocabulary word recognition to reject the word that does not belong to in-vocabulary word or does not belong to correctly recognized word. Utterance verification is an important technology to design a user-friendly speech recognition system. We propose a new utterance verification algorithm for no-training utterance verification system based on the minimum verification error. First, using PBW (Phonetically Balanced Words) DB (445 words), we create no-training anti-phoneme models which include many PLUs(Phoneme Like Units), so anti-phoneme models have the minimum verification error. Then, for OOV (Out-Of-Vocabulary) rejection, the phoneme-based confidence measure which uses the likelihood between phoneme model (null hypothesis) and anti-phoneme model (alternative hypothesis) is normalized by null hypothesis, so the phoneme-based confidence measure tends to be more robust to OOV rejection. And, the word-based confidence measure which uses the phoneme-based confidence measure has been shown to provide improved detection of near-misses in speech recognition as well as better discrimination between in-vocabularys and OOVs. Using our proposed anti-model and confidence measure, we achieve significant performance improvement; CA (Correctly Accept for In-Vocabulary) is about 89％, and CR (Correctly Reject for OOV) is about 90％, improving about 15-21％ in ERR (Error Reduction Rate).

• Journal of Korea Society of Industrial Information Systems
• /
• v.9 no.1
• /
• pp.17-23
• /
• 2004

This paper proposes to determine word senses in Korean language processing by corpus-based ontology learning. Our approach is a hybrid method. First, we apply the previously-secured dictionary information to select the correct senses of some ambiguous words with high precision, and then use the ontology to disambiguate the remaining ambiguous words. The mutual information between concepts in the ontology was calculated before using the ontology as knowledge for disambiguating word senses. If mutual information is regarded as a weight between ontology concepts, the ontology can be treated as a graph with weighted edges, and then we locate the least weighted path from one concept to the other concept. In our practical machine translation system, our word sense disambiguation method achieved a 9％ improvement over methods which do not use ontology for Korean translation.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2003.05b
• /
• pp.366-369
• /
• 2003

본 연구에서는 강건한 문맥의존 음향모델을 작성하기 위한 기초적인 연구로서 문맥환경과 상태수의 변화에 따른 음향모델의 성능을 고찰하고자 한다. 음성은 시간함수로 표현되며 음절, 단어, 연속음성을 발성할때 자음과 모음에 따라 발성시간에 차이가 있으며 음성인식의 최소 인식단위로 널리 사용되는 음소의 앞과 뒤에 오는 문맥환경에 따라 인식성능에 많은 차이를 보이고 있다. 따라서 본 연구에서는 시간의 변화(상태수의 변화)와 상태분할 과정에서 문맥환경의 변화를 고려하여 다양한 형태의 문맥의존 음향모델을 작성하였다. 모델학습은 음소결정트리 기반 SSS 알고리즘(Phonetic Decision Tree-based Successive State Splitting： PDT-555)을 이용하였다 PDT-SSS 알고리즘은 미지의 문맥정보를 해결하기 위해 문맥방향과 시간방향으로 목표 상태수에 도달할 때까지 상태분할을 수행하여 모델을 작성하는 방법이다. 본 연구에서 강건한 문맥의존 음향모델을 학습하기 위한 방법의 유효성을 확인하기 위해 국어공학센터의 452 단어를 대상으로 음소와 단어인식 실험을 수행하였다. 실험결과, 음성의 시간변이에 따른 모델의 상태수와 각 음소의 문맥환경에 따라 인식성능의 변화를 고찰할 수 있었다. 따라서 본 연구는 향후 음성인식 시스템의 강건한 문맥의존 음향모델을 작성하는데 유효할 것으로 기대된다.

• Journal of Navigation and Port Research
• /
• v.41 no.3
• /
• pp.109-118
• /
• 2017

The key word (KW) is a set of words to clearly express the important causations of marine accidents; they are determined by a judge in a Korean maritime safety tribunal. The selection of KW currently has two main issues: one is maintaining consistency due to the different subjective opinion of each judge, and the second is the large number of KW currently in use. To overcome the issues, the systematic framework used to construct KW's needs to be optimized with a minimal number of KW's being derived from a set of Common Words (CW). The purpose of this study is to identify a set of CW to develop the systematic KW construction frame. To fulfill the purpose, the word reduction method to find minimum number of CW is proposed using P areto distribution function and Pareto index. A total of 2,642 KW were compiled and 56 baseline CW were identified in the data sets. These CW, along with their frequency of use across all KW, are reported. Through the word reduction experiments, an average reduction rate of 58.5% was obtained. The estimated CW according to the reduction rates was verified using the Pareto chart. Through this analysis, the development of a systematic KW construction frame is expected to be possible.

• Annual Conference on Human and Language Technology
• /
• 2013.10a
• /
• pp.27-32
• /
• 2013

본 논문은 잘 알려지지 않은 언어 쌍에 대해서 병렬말뭉치(parallel corpus)로부터 자동으로 이중언어 사전을 추출하는 방법을 제안하였다. 이 방법은 중간언어(pivot language)를 매개로 하고 문맥 벡터를 생성하기 위해 공개된 단어 정렬 도구인 Anymalign을 사용하였다. 그 결과로 초기사전(seed dictionary)을 사용한 문맥벡터의 번역 과정이 필요 없으며 통계적 방법의 약점인 낮은 빈도수를 가지는 어휘에 대한 번역 정확도를 높였다. 또한 문맥벡터의 요소 값으로 특정 임계값 이상을 가지는 양방향 번역 확률 정보를 사용하여 상위 5위 이내의 번역 정확도를 크게 높였다. 본 논문은 두 개의 서로 다른 언어 쌍 한국어-스페인어 그리고 한국어-프랑스어 양방향에 대해서 각각 이중언어 사전을 추출하는 실험을 하였다. 높은 빈도수를 가지는 어휘에 대한 번역 정확도는 이전 연구에서 보인 실험 결과에 비해 최소 3.41% 최대 67.91%의 성능 향상을 보였고 낮은 빈도수를 가지는 어휘에 대한 번역 정확도는 최소 5.06%, 최대 990%의 성능 향상을 보였다.

• Journal of Science Education
• /
• v.46 no.1
• /
• pp.17-29
• /
• 2022

The purpose of this study is to look qualitatively into how efficiently and reasonably a computer can learn themes related to the Nature of Science (NOS). In this regard, a corpus has been constructed focusing on literature (920 abstracts) related to NOS, and factors of the optimized Word2Vec (CBOW, Skip-gram) were confirmed. According to the four dimensions (Inquiry, Thinking, Knowledge and STS) of NOS, the comparative evaluation on the word-level word embedding was conducted. As a result of the study, according to the previous studies and the pre-evaluation on performance, the CBOW model was determined to be 200 for the dimension, five for the number of threads, ten for the minimum frequency, 100 for the number of repetition and one for the context range. And the Skip-gram model was determined to be 200 for the number of dimension, five for the number of threads, ten for the minimum frequency, 200 for the number of repetition and three for the context range. The Skip-gram had better performance in the dimension of Inquiry in terms of types of words with high similarity by model, which was checked by applying it to the four dimensions of NOS. In the dimensions of Thinking and Knowledge, there was no difference in the embedding performance of both models, but in case of words with high similarity for each model, they are sharing the name of a reciprocal domain so it seems that it is required to apply other models additionally in order to learn properly. It was evaluated that the dimension of STS also had the embedding performance that was not sufficient to look into comprehensive STS elements, while listing words related to solution of problems excessively. It is expected that overall implications on models available for science education and utilization of artificial intelligence could be given by making a computer learn themes related to NOS through this study.

• The Journal of Korean Association of Computer Education
• /
• v.17 no.5
• /
• pp.99-106
• /
• 2014

The first purpose of the present study is to investigate the way of displaying English words to facilitate phonological loops on the digital screen, and the second purpose is to test whether or not the more effective display type can increase learning rates equally in both low and high foreign language motivation group. To achieve these aims, two experiments were conducted. Experiment 1 showed that 3 times display condition generated higher performances in recall and recognition test than 1 time display condition did. In Experiment 2, we recruited high motivated group and low motivated group in foreign language learning, and assigned each member into 3 times display condition and self-pace condition. The results of Experiment 2 showed that the performance in the low motivated group was higher in the self-pace condition than in 3 times display condition, while this difference was not found in high motivated group. The present results suggest the display type increasing usage of phonological loops in digital screen environments.

• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.73-80
• /
• 2008

In this paper, an advertisement-keyword finding method using document clustering is proposed to solve problems by ambiguous words and incorrect identification of main keywords. News articles that have similar contents and the same advertisement-keywords are clustered to construct the contextual information of advertisement-keywords. In addition to news articles, the web page and summary of a product are also used to construct the contextual information. The given document is classified as one of the news article clusters, and then cluster-relevant advertisement-keywords are used to identify keywords in the document. We could achieve 21% precision improvement by our proposed method.

• Journal of Korea Multimedia Society
• /
• v.8 no.1
• /
• pp.101-110
• /
• 2005

Recently software keyboard is widely used in mobile devices where restrictive hardware keyboard is available. In this paper, new software-driven keyboard input method is proposed, which use minimum number of keyboard input with small keyboard space generated after analyzing of database. In this software keyboard is generated dynamically at each input step by analyzing all possible input words. Software keyboard, only possible key buttons are displayed for minimizing keyboard space and preventing mistyping. And it also provide input word completion function when the number of the candidate words is within threshold scope.