• Speech Sciences
• /
• v.10 no.1
• /
• pp.71-84
• /
• 2003

In the acoustic modeling for large vocabulary speech recognition, a sparse data problem caused by a huge number of context-dependent (CD) models usually leads the estimated models to being unreliable. In this paper, we develop a new clustering method based on the C45 decision-tree learning algorithm that effectively encapsulates the CD modeling. The proposed scheme essentially constructs a supervised decision rule and applies over the pre-clustered triphones using the C45 algorithm, which is known to effectively search through the attributes of the training instances and extract the attribute that best separates the given examples. In particular, the data driven method is used as a clustering algorithm while its result is used as the learning target of the C45 algorithm. This scheme has been shown to be effective particularly over the database of low unknown-context ratio in terms of recognition performance. For speaker-independent, task-independent continuous speech recognition task, the proposed method reduced the percent accuracy WER by 3.93% compared to the existing rule-based methods.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.75-78
• /
• 2003

In this paper, we describe a cross-morpheme pronunciation variation model which is especially useful for constructing morpheme-based pronunciation lexicon for Korean LVCSR. There are a lot of pronunciation variations occurring at morpheme boundaries in continuous speech. Since phonemic context together with morphological category and morpheme boundary information affect Korean pronunciation variations, we have distinguished pronunciation variation rules according to the locations such as within a morpheme, across a morpheme boundary in a compound noun, across a morpheme boundary in an eojeol, and across an eojeol boundary. In 33K-morpheme Korean CSR experiment, an absolute improvement of 1.16％ in WER from the baseline performance of 23.17％ WER is achieved by modeling cross-morpheme pronunciation variations with a context-dependent multiple pronunciation lexicon.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.42 no.3
• /
• pp.131-141
• /
• 2019

Recently the business environment surrounding the financial investment industry is changing rapidly, and the demands of customers (diversity and the cycle of change etc.) are getting shorter. In this context, it can be said that companies are forced to adopt an agile management environment. In particular, non-face-to-face channels, including MTS, is adopting the agile system into the digital finance sector from a company-wide and strategic perspective. This study analyzed the effects of MTS services' environment quality on customer satisfaction and continuous intention to use for MTS users who are rapidly increasing under the agile management environment in the financial investment industry. This study surveyed the quality of service environment (accessibility, convenience, design, security), customer satisfaction, and continuous intention to use for 350 MTS users. First, accessibility, convenience, and security of MTS service environment quality had a positive effect on customer satisfaction, and design was rejected Second, customer satisfaction has a positive effect on continuous intention to use. Third, convenience and security of MTS service environment quality have positive effects on continuous intention to use, and accessibility and design were rejected. The results of this study, together with demographic analysis, are expected to provide useful implications for MTS activation studies and securities firms' strategies.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.34 no.1
• /
• pp.11-28
• /
• 2009

Intelligent investment in setup cost reduction and process reliability improvement is crucial to an emerging integrated lean six sigma practice today. This study examines a cost-minimizing problem of jointly determining production lot size, setup cost reduction, and process reliability improvement decisions for a manufacturer with an imperfect production process. We develop models for previously untapped discrete shipping in a supply chain context as well as continuous shipping and solve them optimally using differential calculus and nonlinear programming. We also conduct analytic and numerical sensitivity analyses to provide various important managerial insights into practices.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.37 no.3
• /
• pp.64-74
• /
• 2014

We show how a supplier can peg cost measures to the reliability of his time guarantees via the penalty costs considered in the framework. The framework also enables us to study the connections between the logistics network and the market. In this context, we show that even when the market base increases significantly, the supplier can still use the logistics network designed to satisfy lower demand density, with only a marginal reduction in profit. Finally we show how the framework is useful to evaluate and compare various logistics system improvement strategies. The supplier can then easily choose the improvement strategy that increases his profit with the minimal increase in his logistics costs.

• Transactions on Control, Automation and Systems Engineering
• /
• v.2 no.4
• /
• pp.255-261
• /
• 2000

This paper presents the results of the robust H(sub)$\infty$ FIR filtering for a class of nonlinear continuous time-varying systems subject to real norm-bounded parameter uncertainty and know Lipschitz nonlinearity under sampled measurements. We address the problem of designing filters, using sampled measurements, which guarantee a prescribed H(sub)$\infty$ performance in continuous time-varying context, irrespective of the parameter uncertainty and unknown initial states. The infinite horizon causal H(sub)$\infty$FIR filter are investigated using the finite moving horizon in terms of two Riccati equations with finite discrete jumps.

• School Mathematics
• /
• v.4 no.4
• /
• pp.677-688
• /
• 2002

The context and intuitive understanding is very important in Statistics Education. Especially, there is a need to mitigate student's difficulty in studying probability density function. One of teaching method this concept is to using relative frequency histogram. But, as using this method, we should know several problems included in that. This study investigate problems in the method for teaching probability density function as gradual meaning of histogram. Also, as alternative approach, this thesis introduce the density curve concept. The application of four methods to teach the concept of the probability density function and analysis of the survey result is done in this research.

• Earthquakes and Structures
• /
• v.3 no.3_4
• /
• pp.271-295
• /
• 2012

This paper presents the solution scheme of using the continuous formulation of 1-D linear member for the dynamic analysis of structures consisting of axially loaded members. The context describes specific applications of such scheme to the verification of experimental data obtained from field test of bridges carried out by a microwave interferometer system and velocimeters. Attention is focused on analysis outlines that may be applicable to in-situ assessment for cable-stayed bridges. The derivation of the dynamic stiffness matrix of a prismatic member with distributed properties is briefly reviewed. A back calculation formula using frequencies of two arbitrary modes of vibration is next proposed to compute the tension force in cables. Derivation of the proposed formula is based on the formulation of an axially loaded flexural member. The applications of the formulation and the proposed formula are illustrated with a series of realistic examples.

• International Journal of Quality Innovation
• /
• v.8 no.3
• /
• pp.188-197
• /
• 2007

In this work, an efficient and easy statistical method to find an equivalent discrete distribution for a continuous random variable (r.v.) is proposed. The proposed method is illustrated by applying it to the treatment of the anthropometrical noise factors in the context of Robust Ergonomic Design.

• The Journal of Information Systems
• /
• v.24 no.1
• /
• pp.1-25
• /
• 2015

Social Network Service (SNS) has been played an important role in the life with the expansion of the modern technology in the cellular communication. More knowledge and understanding should be inevitable even if companies have taken advantage of SNS through word of mouth as one of the new paradigm. In most cases the crucial benefit or peculiarity of SNS has been overlooked because only general aspects of SNS have been applied in the online situation. As a result of this, same paradigm has been considered in reality as SNS was just used one of the marketing tools. However, essential aspects of SNS were investigated to see the relation of usage intention and word of mouth in this study. The hypothesis of the effect of continuous intention of the usage, trust and word of mouth was made and reviewed statistically. The statistical analysis showed there was significant among relationship, context, perceived service quality and continuous intention of the usage. In addition to that, self-expression, relationship, perceived service quality and trust were significant. Finally the continuous intention of the usage and word of mouth was significant as well. Based on this study, SNS provided by the companies could be effective to the customers in terms of word of mouth while different trend was shown in terms of trust.