• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.382-385
• /
• 2007

본 논문은 "X라는 인물은 누구인가?"와 같은 질의어가 주어질 때, X라는 인물에 대한 나이, 직업, 학력 또는 특정 사건에서 X라는 인물의 역할에 대한 정보를 기술하는 문장을 인식하고 추출함으로써 해당 인물에 대한 신문 기사 내용을 요약하는 방법을 제시한다. 질의어 용어에 대해 가능한 많은 관련 문장을 추출하기 위하여 중심 벡터에 기반한 통계적 방법을 적용하였으며, 정확도와 재현율 성능을 개선하기 위해 위키피디어 같은 외부 지식을 사용한 중심 단어의 개선된 가중치 측도를 적용하였다. 실험 대상인 전자신문 말뭉치 상에서 출현 빈도수가 큰 20 인의 IT 인물에 대해 제안한 방법이 개선된 성능을 보임을 알 수 있었다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.6
• /
• pp.813-818
• /
• 2007

This paper is concerned with the problem of recognizing definition sentences. Given a definition question like "Who is the person X?", we are to retrieve the definition sentences which capture descriptive information correspond variously to a person's age, occupation, of some role a person played in an event from the collection of news articles. In order to retrieve as many relevant sentences for the definition question as possible, we adopt a centroid based statistical approach which has been applied in summarization of multiple documents. To improve the precision and recall performance, the weight measure of centroid words is supplemented by using external knowledge resource such as Wikipedia and redundant candidate sentences are removed from candidate definitions. We see some improvements obtained by our approach over the baseline for 20 IT persons who have high document frequency.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.31 no.9C
• /
• pp.853-858
• /
• 2006

TMHMM(Tied Mixture Hidden Markov Model) is an important approach to reduce the number of free parameters in speech recognition. However, this model suffers from a degradation in recognition accuracy due to its GPDF (Gaussian Probability Density Function) clustering error. This paper proposes a clustering algorithm, called HCNN(Homogeneous Centroid Neural network), to cluster acoustic feature vectors in TMHMM. Moreover, the HCNN uses the heterogeneous distance measure to allocate more code vectors in the heterogeneous areas where probability densities of different states overlap each other. When applied to Korean digit isolated word recognition, the HCNN reduces the error rate by 9.39% over CNN clustering, and 14.63% over the traditional K-means clustering.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.2
• /
• pp.423-428
• /
• 2017

These days, various and tons of education information are rapidly increasing and spreading due to Internet and smart devices usage. Recently, as e-Learning usage increasing, many instructors and students (learners) need to set a goal to maximize learners' result of education and education system efficiency based on big data analytics via online recorded education historical data. In this paper, the author applied Word2Vec algorithm (neural network algorithm) to find similarity among education words and classification by clustering algorithm in order to objectively recognize and analyze online recorded education historical data. When the author applied the Word2Vec algorithm to education words, related-meaning words can be found, classified and get a similar vector values via learning repetition. In addition, through experimental results, the author proved the part of speech (noun, verb, adjective and adverb) have same shortest distance from the centroid by using clustering algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3257-3269
• /
• 2020

Articulation disorders are characterized by an inability to achieve clear pronunciation due to misuse of the articulators. In this paper, a method of detecting such disorders by comparing to the standard pronunciations is proposed. This method defines the standard pronunciations from the speeches of normal children by clustering them with three features which are the Linear Predictive Cepstral Coefficient (LPCC), the Mel-Frequency Cepstral Coefficient (MFCC), and the Relative Spectral Analysis Perceptual Linear Prediction (RASTA-PLP). By calculating the distance between the centroid of the standard pronunciation and the inputted pronunciation, disordered speech whose features locates outside the cluster is detected. 89 children (58 of normal children and 31 of children with disorders) were recruited. 35 U-TAP test words were selected and each word's standard pronunciation is made from normal children and compared to each pronunciation of children with disorders. In the experiments, the pronunciations with disorders were successfully distinguished from the standard pronunciations.

• Journal of the Korean Society for information Management
• /
• v.18 no.3
• /
• pp.159-178
• /
• 2001

This paper presents an automatic text summarization model which selects representative sentences from sentence clusters to create a summary. Summary generation experiments were performed on two sets of test documents after learning the optimum environment from a training set. Centroid clustering method turned out to be the most effective in clustering sentences, and sentence weight was found more effective than the similarity value between sentence and cluster centroid vectors in selecting a representative sentence from each cluster. The result of experiments also proves that inverse sentence weight as well as title word weight for terms and location weight for sentences are effective in improving the performance of summarization.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.2
• /
• pp.196-205
• /
• 1991

This paper is a study on the isolated word recognition of speaker independent which proposes to newly improved MSVQ(multisection vector quantization) recognition system which improve the classical MSVQ recognition system. It is a difference that test pattern has on more section than reference pattern in recognition system 146 DDD area names are selected as recognition vocabulary. 12th LPC cepstral coefficients is used as feature parameter. and when codebook is generated, MINSUM and MINMAX are used in finding the centroid. According to the experiment result. it is proved that this method is better than VQ(vector quantization) recognition methods, DTW(dynamic time warping) pattern matching methods and classical MSVQ methods for recognition rate and recognition time.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.4
• /
• pp.306-310
• /
• 2002

In this paper, we realized a system that converts the Korean alphabet (Hangul) images, which are in any domain that is formed by the finger movement on the Hangul document, to the editable characters and then outputs them to the word editor. The domain of hand is separated from the sphere of document in the pre-process step of image. The centroid point of hand is drawn by the maximum circular movement method. After the system recognizes the hand with the circular pattern vector algorithm, finds out the position of finger by the distance spectrum and then draws out the sphere of selected character image by the finger movement to divide the characters into character units by applying the histogram between the Hangul characters. We standardized the characters of various sizes. We used the circular pattern vector algorithm that grafts on the fuzzy inference to divert the character images of the domain, which user wants, to the editable characters by comparing the characteristic vectors between the standard pattern character and the inputted character and by recognizing the character.

• The Journal of the Acoustical Society of Korea
• /
• v.8 no.5
• /
• pp.102-112
• /
• 1989

In this paper, we proposed the study on speaker-independent isolated word recognition for DDD area-name using vector quantization and chose total 146 DDD area-name to recognize words for application of dialing system. We made the codebook using 12th LPC cepstrum coefficients and used the minsum and the minimax method to find the centroid and we applied 3 splitting rule to a codebook generation. The single section and the multi section with time information were used to generate the codebooks and the over-lapped section codebook was used, too. From the experiment result, we proved that the minsum method was better than the minimax method and the evaluation of the system yielded an accuracy of about 90 percents In case of speaker-independent.