• ETRI Journal
• /
• v.28 no.6
• /
• pp.811-814
• /
• 2006

In this letter, we introduce confusion-based confidence measures for detecting an impostor in speaker recognition, which does not require an alternative hypothesis. Most traditional speaker verification methods are based on a hypothesis test, and their performance depends on the robustness of an alternative hypothesis. Compared with the conventional Gaussian mixture model-universal background model (GMM-UBM) scheme, our confusion-based measures show better performance in noise-corrupted speech. The additional computational requirements for our methods are negligible when used to detect or reject impostors.

• Journal of the Society of Naval Architects of Korea
• /
• v.46 no.1
• /
• pp.57-68
• /
• 2009

In automotive industries, reusability of product information is increasing through database construction of previous product data. The product data is stored by data quality management in product information systems. For naval ships, have the functional similarity by the ships of the same classification and class, that are built by series. Information of hull structures as well as embarked equipments are similar. So it would be effective to use database systems that are considered product information quality of previous ships in design and production processes. In this paper we discuss product information quality in database construction of naval ship product models. For this, we propose a basic concept and reference model for data quality verification. Based on this concept, A verification guideline is defined and it is applied for the case study of the digital naval ship which was built to the naval ship product model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.5
• /
• pp.828-836
• /
• 2008

This paper suggests a method for verification of temporal relations on SMIL 2.0 document using an extended temporal interval model. The SMIL 2.0 document has more asynchronous temporal relations and supports more interactive relations between objects than traditional SMIL document. But it is higher to produce temporal inconsistency by various interactive relations between objects. So the suggested verification method expresses SMIL 2.0 document as functional relations based on an extended temporal interval model and verifies SMIL 2.0 document using interactive relations and temporal intervals between objects. Applications to the verification method are as follows; multiuser interactive contents, online-learning, etc.

• 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).

• International Journal of Aeronautical and Space Sciences
• /
• v.18 no.1
• /
• pp.108-117
• /
• 2017

This paper presents a distribution simulation model for dual purpose improved conventional munitions based on flight test data. A systematic procedure for designing a dispersion simulation model is proposed. A new accumulated broken line graph was suggested for designing the distribution shape. In the process of verification and simulation for the distribution simulation model, verification was performed by first comparing data with firing test results, and an application simulation was then conducted. The Monte Carlo method was used in the simulations, which reflected the relationship between ejection conditions and real distribution data. Before establishing the simulation algorithm, the dominant ejection parameter of the submunitions was examined. The relationships between ejection conditions and distribution results were investigated. Five key distribution parameters were analyzed with respect to the ejection conditions. They reflect the characteristics of clustered particle dynamics and aerodynamics.

• Journal of Information Technology Services
• /
• v.19 no.3
• /
• pp.151-163
• /
• 2020

This paper describes a study on the FRACAS(Failure Reporting Analysis and Corrective Action System)-based dependability control platform for domestic urban railway trains. There are more demands for the verification of the dependability of trains as it becomes a regulation for train manufacturers to verify the dependability recently. Train manufacturers as well as railway operators need a effective FRACAS solution to perform the verification of the dependability. Yet current FRACAS solutions have limitations to support the verification processes effectively. This paper addresses the issues of current FRACAS solutions and suggests a FRACAS framework designed for the domestic urban railway trains. Service failure scenarios are standardized using the proposed availability model to implement a more user-friendly and reliable platform. A new FRACAS-based platform for the dependability control (SCARF^®) has been developed to implement the suggested framework. The detail interfaces and functions of the platform are explained. The SCARF^® platform is expected to engage the increasing demands for the dependability control successfully enhancing the reliability, maintainability, availability and safety of domestic urban railway trains eventually.

• Journal of Ocean Engineering and Technology
• /
• v.27 no.1
• /
• pp.24-30
• /
• 2013

The Korea Navy has been making constant efforts to apply M&S (modeling and simulation) to naval ship development, and the generalization of M&S for ship development is a trend. M&S for ship design is used for the V&V (verification and validation) of its design and operation, including design verification and ergonomic design that considers the crew using the Naval Ship Product Model. In addition, many parts of this M&S are repeatedly accomplished regardless of the kinds of ships. This study aims to standardize M&S, which repeatedly applies similar verifications for operation scenarios. A congestion assessment simulation for the major spaces of ships was the subject of the standardization based on the leading research results of various researchers, and a simulation automation solution was suggested. An information model using XML was proposed through the simulation automation concept, and a prototype system based on it was implemented. The usability was shown through a case study that verified the operability performance of the crew messroom.

• Journal of the Korean Society of Systems Engineering
• /
• v.19 no.1
• /
• pp.44-55
• /
• 2023

The defense M&S system, which has been classified as a weapon system between requirements determination and project implementation, is being developed by applying the weapon system development procedure of the Defense Acquisition Program Administration. The M&S system abstracts and models the real world to suit the intended use and proceeds with the process of developing it as a software-oriented system. Overseas, the conceptual model development stage is staged before entering the design stage after the requirements analysis. In addition, each step includes verification and validation processes. In Korea, while establishing and applying the weapon system development procedure based on the SE process, the M&S system is also applied in the same way as the general weapon system, limiting appropriate development outputs and verification and validation. In this study, the system development procedure of the M&S system is established and presented based on the relevant standards and SE process of developed countries.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.3
• /
• pp.268-272
• /
• 2009

In this paper, we propose a Gaussian Mixture Model (GMM) based incremental robust adaptation with a forgetting factor for the speaker verification. Speaker recognition system uses a speaker model adaptation method with small amounts of data in order to obtain a good performance. However, a conventional adaptation method has vulnerable to the outlier from the irregular utterance variations and the presence noise, which results in inaccurate speaker model. As time goes by, a rate in which new data are adapted to a model is reduced. The proposed algorithm uses an incremental robust adaptation in order to reduce effect of outlier and use forgetting factor in order to maintain adaptive rate of new data on GMM based speaker model. The incremental robust adaptation uses a method which registers small amount of data in a speaker recognition model and adapts a model to new data to be tested. Experimental results from the data set gathered over seven months show that the proposed algorithm is robust against outliers and maintains adaptive rate of new data.

• The Journal of Information Systems
• /
• v.29 no.1
• /
• pp.137-158
• /
• 2020

Purpose This study aims to analyze how entrepreneurs' morality affects entrepreneurship and social responsibility. The purpose of this study is to analyze the differences of entrepreneurship and social responsibility on corporate financial performance and social performance by measuring entrepreneurial morality index. Design/methodology/approach The research model is based on the existing literature related to morality, entrepreneurship, social responsibility, and corporate performance. In order to verify the research model, empirical analysis was conducted. The collected data were analyzed by Smart-pls 2.0 based on the structural equation model based measurement model verification and the structural model verification two - step approach. Using the bootstrapping method of PLS, 500 samples were constructed and hypothesis verification was performed. Findings The results of this study are as follows. In the case of general manufacturing companies, business people are more focused on improving corporate performance than morality, and have a somewhat consistent effect with entrepreneurial spirit that does not have a space of morality. When entrepreneurship is strengthened, financial performance and social performance. Business entrepreneurs in social enterprises are more aware of social responsibility than entrepreneurship, so they achieve both financial performance and social performance at the same time. As a result of this study, it was found that there is a difference in perception depending on the morality of the business people, entrepreneurship, social bookkeeping, and management performance according to the type of company.