• The Journal of the Acoustical Society of Korea
• /
• v.16 no.3E
• /
• pp.19-23
• /
• 1997

The goal of postprocessing in automatic speech recognition is to improve recognition performance by utterance verification at the output of recognition stage. It is focused on the effective rejection of out-of vocabulary words based on the confidence score of hypothesized candidate word. We present two methods for computing confidence scores. Both methods are based on the distance between each observation vector and the representative code vector, which is defined by the most likely code vector at each state. While the first method employs simple time normalization, the second one uses a normalization technique based on the concept of on-line garbage mode[1]. According to the speaker independent isolated words recognition experiment with discrete density HMM, the second method outperforms both the first one and conventional likelihood ratio scoring method[2].

• The Journal of the Acoustical Society of Korea
• /
• v.17 no.2E
• /
• pp.26-30
• /
• 1998

In this paper, we compose neural network predictive HMM(NNPHMM) to provide the dynamic feature of the speech pattern for the HMM. The NNPHMM is the hybrid network of neura network and the HMM. The NNPHMM trained to predict the future vector, varies each time. It is used instead of the mean vector in the HMM. In the experiment, we compared the recognition abilities of the one hundred Korean syllables according to the variation of hidden layer, state number and prediction orders of the NNPHMM. The hidden layer of NNPHMM increased from 10 dimensions to 30 dimensions, the state number increased from 4 to 6 and the prediction orders increased from 10 dimensions to 30 dimension, the state number increased from 4 to 6 and the prediction orders increased from the second oder to the fourth order. The NNPHMM in the experiment is composed of multi-layer perceptron with one hidden layer and CMHMM. As a result of the experiment, the case of prediction order is the second, the average recognition rate increased 3.5% when the state number is changed from 4 to 5. The case of prediction order is the third, the recognition rate increased 4.0%, and the case of prediction order is fourth, the recognition rate increased 3.2%. But the recognition rate decreased when the state number is changed from 5 to 6.

• The Journal of the Korea Contents Association
• /
• v.10 no.6
• /
• pp.450-459
• /
• 2010

The purpose of this study is to difference of the recognition for self-efficacy which staffs of deluxe hotel. This study aimed at: The first, I measure recognizing for self-efficacy which staffs at the first grade Hotel and the second grade hotel. The second, self-efficacy is factor analyzes for the study. The third, I study a difference of self-efficacy the first grade Hotel and between the second grade Hotel staffs. The fourth, I study whether there is a difference in recognition of self-efficacy by each demographic characteristic in Hotel staffs. To research and analyze, survey was conducted to 400 employees working at deluxe hotels in Seoul and 352 survey data were analyzed. The results come up with: The first, As for the recognition of self-efficacy the first grade Hotel and the second grade Hotel staffs, there was the difference that a level of significance. The second, marriage, major, educational background, work period and income level were the difference that a level of significance.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 1999.11a
• /
• pp.132-135
• /
• 1999

In this work, two approaches were proposed for the recognition of partial discharge patterns. The first approach was neural network with backpropagation algorithm, and the second approach was angle calculation between two operator vectors. PD signal were detected using three electrode systems; IEC(b), needle-plane and CIGRE method II electrode system. Both of neural network and angle comparison method showed good recognition performance for the patte군 similar to the trained patterns. And the number of operators to be used had a great influence on the recognition performance to the untrained patterns.

• The Korean Journal of Health Service Management
• /
• v.11 no.1
• /
• pp.131-142
• /
• 2017

Objectives : This study aimed to examine to relevance of socioeconomic class recognition and subjective health status of injured workers. Methods : We used data collected over 3years by the Panel Study of Worker's Compensation Insurance(PSWCI; 2015). Data was analyzed using the chi-square test and logistic regression using SPSS ver. 22.0 to verify the relevance between the socioeconomic class recognition and general characteristics of injured workers. Results : First, the income groups of first class, second class and third class were analyzed as being of lower socioeconomic class status, and the income group four class and five class was analyzed as being the middle-ower the socioeconomic class status. Second, the better the subjective health status, higher the perception of socioeconomic class status, as analyzed by Model 1 using only the parameters of socioeconomic status recognition and Model 2 and Model 3 using income class and general characteristics. Conclusions : Health and industrial accident policies are needed to improve awareness of socioeconomic class status of injured workers.

• Hwankyungkyoyuk
• /
• v.10 no.2
• /
• pp.157-174
• /
• 1997

The purpose of this thesis is to study recognition and attitude between teachers and students about school environmental education. The data for this study were collected by administering interviews with seven hundred sixty three teachers and one thousand six hundred fifty six students, and make comparison between these teachers and students recognition and attitude for the environmental education by use of research are as follows. The conclusion of this research are as follows. First, In the study of teachers and students recognition and attitudes about environmental education, though they are interested in it, they lack in knowledge and ability to solve real environmental problems. Also, environmental education tends to be dealt with indifferently and formally because of the burden of entrance examination and lack of material concerned. Second, the recognition and attitude of the teacher-student group about the school environmental education have meaningful difference in each region. The suggestions for the improvement of the environmental education based on these conclusions are as follows. First, the more efficient methods and materials of the school environmental education must be developed in order that students may understand the complex property of the environment and at the same time have the ability to improve the environmental quality. Second, the cooperating system of environmental education including the teacher- student- student's parents' should be established in order to develop the recognition and attitudes for the environment. And also for teachers group to get the more professional leadership about environmental education, government' support is needed.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.12C
• /
• pp.984-994
• /
• 2010

Pose variation is a critical problem in face recognition. Three-dimensional(3D) face recognition techniques have been proposed, as 3D data contains depth information that may allow problems of pose variation to be handled more effectively than with 2D face recognition methods. This paper proposes a pose-normalized 3D face modeling method that translates and rotates any pose angle to a frontal pose using a plane fitting method by Singular Value Decomposition(SVD). First, we reconstruct 3D face data with stereo vision method. Second, nose peak point is estimated by depth information and then the angle of pose is estimated by a facial plane fitting algorithm using four facial features. Next, using the estimated pose angle, the 3D face is translated and rotated to a frontal pose. To demonstrate the effectiveness of the proposed method, we designed 2D and 3D face recognition experiments. The experimental results show that the performance of the normalized 3D face recognition method is superior to that of an un-normalized 3D face recognition method for overcoming the problems of pose variation.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.24 no.4
• /
• pp.343-348
• /
• 2014

Face recognition system has advanctage to automatically recognize a person without causing repulsion at deteciton process. However, the face recognition system has a drawback to show lower perfomance according to illumination variation unlike the other biometric systems using fingerprint and iris. Therefore, this paper proposed a robust face recogntion method against illumination varition by slective fusion technique using both visible and infrared faces based on fuzzy linear disciment analysis(fuzzy-LDA). In the first step, both the visible image and infrared image are divided into four bands using wavelet transform. In the second step, Euclidean distance is calculated at each subband. In the third step, recognition rate is determined at each subband using the Euclidean distance calculated in the second step. And then, weights are determined by considering the recognition rate of each band. Finally, a fusion face recognition is performed and robust recognition results are obtained.

• Journal of Biomedical Engineering Research
• /
• v.20 no.6
• /
• pp.573-581
• /
• 1999

Although phonocardiography by auscultation has been used in diagnosis long time ago, recognition of heart sound was tried only restricted fields such as the first heart sound, the second heart sound, and specific valve operation for the purpose of analyzing local function or operation of heart and developments of heart sound recognition in full cycle are quite insignificant. in this paper, we proposed a recognition method which extracts features of heart sound in full cycle and classllies heart sounds This proposed recognition algorithm is based on detecting the first and second heart sounds in thme domain. The algorithm classifics heart sound into several classes by extracting the important time blocks and analyzing the peak position, integration values and statistical variables. Heart sounds are classified into normal, early systolic murmur, late systolic mumur, early diastolic murmur, late diastolie murmur, continuous murmur. We can verify our algorithm is useful from the results which show the average recognition rate of heart sounds is 88 perecnt. Recognition error was occurred mainly in early systolic murmur.

• MALSORI
• /
• no.51
• /
• pp.151-165
• /
• 2004

For educational and research purposes, a Korean speech recognition platform is designed. It is based on an object-oriented architecture and can be easily modified so that researchers can readily evaluate the performance of a recognition algorithm of interest. This platform will save development time for many who are interested in speech recognition. The platform includes the following modules: Noise reduction, end-point detection, met-frequency cepstral coefficient (MFCC) and perceptually linear prediction (PLP)-based feature extraction, hidden Markov model (HMM)-based acoustic modeling, n-gram language modeling, n-best search, and Korean language processing. The decoder of the platform can handle both lexical search trees for large vocabulary speech recognition and finite-state networks for small-to-medium vocabulary speech recognition. It performs word-dependent n-best search algorithm with a bigram language model in the first forward search stage and then extracts a word lattice and restores each lattice path with a trigram language model in the second stage.