• Proceedings of the Acoustical Society of Korea Conference
• /
• 1995.06a
• /
• pp.83-87
• /
• 1995

Keyword Spotting 이란 음성인식의 한 분야로서 입력된 음성에서 미리 정해진 특정단어 또는 복수 개의 단어들 중 어느 것이 포함되어 있는지의 여부를 찾아내고 이 단어를 식별해 내는 작업을 의미한다. 음소모델을 이용하여 Keyword Spotting 시스템을 구성할 경우 새로운 keyword의 추가 또는 변경이 필요할 때 단순히 그 발음사전에 따라 음소모델들을 연결시킴으로써 keyword 모델을 구성할 수 있으므로 단어모델에 의한 방법에 비해 장점이 있다. 본 논문에서는 triphone을 기본단위로 하는 HMM 에 의해 keyword 모델을 구성하고, non-keyword 모델 및 silence 모델을 함께 사용하는 keyword spotting 시스템을 구성하였다. 이러한 시스템에서 non-keyword 모델은 keyword와 keyword가 아닌 음성을 구분 지어주는 역할을 하므로 인식성능의 향상을 위해서는 적절한 non-keyword 모델의 선택이 필요하다. 본 논문에서는 10개의 state를 갖는 단일모델, 조음방법에 의해 음소들을 clustering 한 모델, 그리고 통계적 방법에 의해 음소들을 clustering 한 모델들을 각각 non-keyword 모델로 사용하여 그 성능을 비교하였다. 6개의 keyword를 대상으로 한 화자독립 keyword spotting 실험결과, 통계적 방법에 의해 음소들을 6 또는 7개의 그룹으로 clustering 한 방법이 가장 우수한 인식성능을 나타냈다.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1994.06c
• /
• pp.249-252
• /
• 1994

Keyword spotting 이란 음성인식의 한 분야로서 컴퓨터가 사람의 음성을 입력받아 이 음성에 미리 정해진 특정단어 또는복수개의 단어들 중 어느 것이 포함되어 있는지의 여부를 찾아내고 이 단어를 식별해 내는 작업을 의미한다. 이러한 keyword spotting 시스템의 인식 오류들을 감소시키는 방법의 하나로 keyword spotting 시스템에 후처리 과정을 둠으로써 잘못 검출된 keyword 들을 제거시키는 방법이 사용될 수 있다. 본 논문에서는 keyword로 검출된 영역에 대한 keyword 모델의 likeihood와 그 여역에 대한 filler 모델의 likelihood의 ratio 와 second best keyword 의 likelihood 그리고, 끝점존재 영역의 구간 길이등 여러 가지 정보를 이용한 후처리과정을 검토하고 인식실험을 통해 이들의 성능을 비교하였다. 6개의 부서명을 keyword로 하는 불특정 화자 keyword spotting 실험을 수행한 결과 baseline 시스템의 경우 고립단어 및 문장 형태의 음성에 대해 95.0%의 keyword 인식률을 얻었으며, 본 논문에서 검토된 네 가지 후처리 방법에 의해 keyword rejection ratio를 0%에서 5%까지 변화시켜 나갈 경우 최저 95.3%에서 최고 97.1%까지 keyword 인식률이 향상된 결과를 얻었다. 특히 성능과 계산량을 종합적으로 고려할 때 끝점 존재 영역의 구간 길이 정보를 이용한 방법이 가장 우수하였다.

• Speech Sciences
• /
• v.10 no.3
• /
• pp.225-239
• /
• 2003

In this paper, we develop a keyword spotting system using vocabulary-independent speech recognition technique, and investigate several non-keyword modeling and post-processing methods to improve its performance. In order to model non-keyword speech segments, monophone clustering and Gaussian Mixture Model (GMM) are considered. We employ likelihood ratio scoring method for the post-processing schemes to verify the recognition results, and filler models, anti-subword models and N-best decoding results are considered as an alternative hypothesis for likelihood ratio scoring. We also examine different methods to construct anti-subword models. We evaluate the performance of our system on the automatic telephone exchange service task. The results show that GMM-based non-keyword modeling yields better performance than that using monophone clustering. According to the post-processing experiment, the method using anti-keyword model based on Kullback-Leibler distance and N-best decoding method show better performance than other methods, and we could reduce more than 50% of keyword recognition errors with keyword rejection rate of 5%.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.3
• /
• pp.143-150
• /
• 2019

This study aimed to analyze the keyword related to Health Disparity in Korea through the method of keyword network analysis and to establish a basic database for suggesting ideas for prospective studies in physical education. To achieve the goal, this study crawled co-occured keyword with 'health' and 'disparity' from news casted in 20 different channels. The duration of the news was 3 months, from September 11th, 2018 to December 11th. The results are as follows. First, among the news during recent 3 months, there were 1,383 keyword related to health disparity and this study selected 173 keyword which had co-occured over 3 times. Second, the inclusiveness of the network was 97.674% and the density was .038. Third, analyzing news related to health disparity, 'mortality' was the most co-occured keyword and 'disparity', 'reinforcement', 'the most', 'health', '6 times', 'Seoul', 'half', 'medicine', and 'local' were shown similarly. And common keyword in 4 centrality were 13 keyword. Lastly, by analyzing eigenvector centrality, significantly different result has shown. 'Disparity' was the most co-occured keyword. Based on this result, this study showed the necessity for reinforcing the public physical education in public education system in Korea. In order to achieve it, the field of physical education must look beyond present elite-focused physical education to public physical activity.

• Journal of Sasang Constitutional Medicine
• /
• v.25 no.1
• /
• pp.34-42
• /
• 2013

Objectives The purpose of this study was analyzing the equality between the MeSH terms and the keyword used in the papers published in Journal of Sasang Constitutional Medicine and investigating how to use an appropriate MeSH terms as keyword in the papers. Methods A total of 704 keyword used in 177 papers published from 2009 to 2012 in Journal of Sasang Constitutional Medicine were analyzed to investigate the equality between the keyword and the MeSH terms. The collected data was analyzed using SPSS 17.0 software for frequency analysis. Results Among the 704 keyword, 107 keyword(15.2%) was perfectly matched with the MeSH terms. 64 keyword(9.1%) showed partial difference was with the MeSH terms, and 11 keyword(1.7%) showed partial difference was with the Entry terms. 127 keyword(18.0%) were included in the exception item due to the nature of journal, and 395 keyword(56.1%) were not perfectly matched with the MeSH terms. In the yearly analysis result, the number of papers that keyword and MeSH terms perfectly matched was not significant changed, however the number of papers that keyword and MeSH terms did not matched was continuously increased, which clearly indicate use of MeSH terms as the keyword of the papers published in the journal of Sasang constitution medicine is insufficient. Conclusions The papers published in journal of Sasang constitutional medicine need to be cited in various fields and the paper's finding need to affect in other studies for the development of Korean medicine and Sasang constitutional medicine. The use of proper keyword aligned with the international standards is necessary to accomplish the globalization of them.

• KIISE Transactions on Computing Practices
• /
• v.22 no.5
• /
• pp.246-251
• /
• 2016

Recently, the influence of SNS and online media is rapidly growing with a consequent increase in the interest of marketing using these tools. Blog marketing can increase the ripple effect and information delivery in marketing at low cost by prioritizing keyword search results of influential portal sites. However, because of the tough competition to gain top ranking of search results of specific keywords, long-term and proactive efforts are needed. Therefore, we propose a new method that recommends associated keyword groups with the possibility of higher exposure of the blog. The proposed method first collects the documents of blog including search results of target keyword, and extracts and filters keyword with higher association considering the frequency and location information of the word. Next, each associated keyword is compared to target keyword, and then associated keyword group with the possibility of higher exposure is recommended considering the information such as their association, search amount of associated keyword per month, the number of blogs including in search result, and average writhing date of blogs. The experiment result shows that the proposed method recommends keyword group with higher association.

• 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.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.7
• /
• pp.319-324
• /
• 2006

We Propose two new methods for non-keyword modeling to improve the performance of speaker- and vocabulary-independent keyword spotting system. The first method is decision tree clustering of monophone at the state level instead of monophone clustering method based on K-means algorithm. The second method is multi-state multiple mixture modeling at the syllable level rather than single state multiple mixture model for the non-keyword. To evaluate our method, we used the ETRI speech DB for training and keyword spotting test (closed test) . We also conduct an open test to spot 100 keywords with 400 sentences uttered by 4 speakers in an of fce environment. The experimental results showed that the decision tree-based state clustering method improve 28%/29% (closed/open test) than the monophone clustering method based K-means algorithm in keyword spotting. And multi-state non-keyword modeling at the syllable level improve 22%/2% (closed/open test) than single state model for the non-keyword. These results show that two proposed methods achieve the improvement of keyword spotting performance.

• Journal of the Korea Convergence Society
• /
• v.9 no.9
• /
• pp.9-14
• /
• 2018

This study aims to investigate an importance of Author keyword with analysis the position of author keyword. An analysis was carried out on the position of author keyword. we examined an importance of Author keyword by using degree centrality, closeness centrality, betweenness centrality, eigenvector centrality. In the next stage, we performed analysis on correlation between network centrality measures and the position of keyword. As a result, degree centrality, closeness centrality, betweenness centrality, eigenvector centrality both has a high value in 4th author keyword order. eigenvector centrality was the comparatively effective method to separate of author keyword order method than other 3 centrality. Correlation analysis result shows that the network analysis value are increasing in order. This study has significance in that it was able to examine the author keyword behavior. Future research is needed to identify and supplement future situational factors, behavior, and psychology.

• Journal of the Korean Society for information Management
• /
• v.31 no.2
• /
• pp.121-142
• /
• 2014

This study aims to investigate the importance of author keyword with analysis the position of author keyword in journal. In the first stage, an analysis was carried out on the position of author keyword. We examined the importance of author keyword by using degree centrality, closeness centrality, betweenness centrality, eigenvector centrality and effective size of structural hole. In the next stage, We performed analysis on correlation between network centrality measures and the position of author keyword. The result of correlation analysis on network centrality measures and the position of author keyword shows that there are the more significant areas of the result of the correlation analysis on degree centrality, betweenness centrality and the position of keyword. In addition, These results show that we need to consider that the possible way as measuring the importance of author keyword in journal is not only a term frequency but also degree centrality and betweenness centrality.