• Cross-Cultural Studies
• /
• v.52
• /
• pp.111-132
• /
• 2018

The way of approaching 'the relationship between love and justice' varies from person to person. We can argue for superiority of love or for superiority of justice by understanding the relationship between the two as conflicting. We can also argue that we need each other by understanding each other as a complementary relationship rather than an oppositional relationship. Hegel, however, sees love and justice as independent constitutive principles valid in different areas and does not regard the two as opposing nor complementary. This can only be understood when the structure of Hegel's theory of recognition is properly assumed. The relationship between love and justice will be considered mainly in Hegel's theory of recognition. Key philosophical points of Hegel's theory of recognition and consequences drawn on the relationship between love and justice on the basis of the theory will be examined. This can be summarized in the form of a thesis, roughly as follows. - Hegel presents love, justice and solidarity, that are various forms of recognition, to a family, a civil society and a state, that are three forms of social relations, as their constitutive principles. He does not grasp the relationship between love and justice as oppositional nor as complementary, that is different from many people's general perspective on the relationship of the two. - In Hegel's theory of recognition, love and justice differ in the areas in which they are valid. Love is a valid principle in the intimacy, and justice is a valid principle in non-intimacy. So, if justice and rights are asserted in intimacy, the area of intimacy is destroyed. Conversely, if love is asserted in non-intimacy, it cannot exercise real influence. - In the political community such as a state, where intimacy and non-intimacy overlap each other, the principle of solidarity is needed as a new constitutive principle, since a state does not stand on the principle of love as in a family nor on the principle of justice as in a civil society.

• Speech Sciences
• /
• v.8 no.4
• /
• pp.17-33
• /
• 2001

In this paper, we implement the large variable vocabulary speech recognition system, which is characterized by no additional pre-training process and no limitation of recognized word list. We have designed the system in order to achieve the high recognition rate using the decision tree based state tying algorithm and in order to reduce the processing time using the gaussian selection based variable flooring algorithm, the limitation algorithm of the number of nodes and ENNS algorithm. The gaussian selection based variable flooring algorithm shows that it can reduce the total processing time by more than half of the recognition time, but it brings about the reduction of recognition rate. In other words, there is a trade off between the recognition rate and the processing time. The limitation algorithm of the number of nodes shows the best performance when the number of gaussian mixtures is a three. Both of the off-line and on-line experiments show the same performance. In our experiments, there are some differences of the recognition rate and the average recognition time according to the distinction of genders, speakers, and the number of vocabulary.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.6
• /
• pp.1233-1242
• /
• 2017

Various attempts have been made to prevent crime risk. One of the cases where outdoor pedestrians are attacked by criminals is the abnormal health condition. When a mental or mental condition that can not sustain normal walking due to drunkenness is exposed, the case of being a crime is revealed through crime case analysis. In this study, we propose a method for estimating the state of an individual that can be detected in outdoor activities. In order to avoid the inconvenience of installing a separate terminal for event information transmission of sensors and sensors, it is possible to estimate an abnormal state by using a 3-axis acceleration sensor built in a smart phone. The state of the user can be estimated by analyzing the momentum of the user and analyzing it with the passage of time. It is possible to distinguish the flow of time at regular intervals, to recognize the activity patterns in each time band, and to distinguish between normal and abnormal. In this study, we have evaluated the total amount of kinetic energy and kinetic energy in each direction of the acceleration sensor and the Fourier transformed value of the total energy amount to distinguish the abnormal state.

• Speech Sciences
• /
• v.5 no.1
• /
• pp.7-21
• /
• 1999

This paper proposes an improved training procedure in speech recognition based on the continuous density of the Hidden Markov Model (CDHMM). Of the three parameters (initial state distribution probability, state transition probability, output probability density function (p.d.f.) of state) governing the CDHMM model, we focus on the third parameter and propose an efficient algorithm that determines the p.d.f. of each state. It is known that the resulting CDHMM model converges to a local maximum point of parameter estimation via the iterative Expectation Maximization procedure. Specifically, we propose two independent algorithms that can be embedded in the segmental K -means training procedure by replacing relevant key steps; the adaptation of the number of mixture Gaussian p.d.f. and the initialization using the CDHMM parameters previously estimated. The proposed adaptation algorithm searches for the optimal number of mixture Gaussian humps to ensure that the p.d.f. is consistently re-estimated, enabling the model to converge toward the global maximum point. By applying an appropriate threshold value, which measures the amount of collective changes of weighted variances, the optimized number of mixture Gaussian branch is determined. The initialization algorithm essentially exploits the CDHMM parameters previously estimated and uses them as the basis for the current initial segmentation subroutine. It captures the trend of previous training history whereas the uniform segmentation decimates it. The recognition performance of the proposed adaptation procedures along with the suggested initialization is verified to be always better than that of existing training procedure using fixed number of mixture Gaussian p.d.f.

• Journal of Korea Society of Industrial Information Systems
• /
• v.6 no.3
• /
• pp.107-114
• /
• 2001

This paper describes Connected Digit Recognition with Considering Acoustic Feature in Korea. The recognition rate of connected digit is usually lower than word recognition. Therefore, speech feature parameter and acoustic feature are employed to make robust model for digit, and we could confirm the effect of Considering. Acoustic Feature throughout the experience of recognition. We used KLE 4 connected digit as database and 19 continuous distributed HMM as PLUs(Phoneme Like Units) using phonetical rules. For recognition experience, we have tested two cases. The first case, we used usual method like using Mel-Cepstrum and Regressive Coefficient for constructing phoneme model. The second case, we used expanded feature parameter and acoustic feature for constructing phoneme model. In both case, we employed OPDP(One Pass Dynamic Programming) and FSA(Finite State Automata) for recognition tests. When appling FSN for recognition, we applied various acoustic features. As the result, we could get 55.4% recognition rate for Mel-Cepstrum, and 67.4% for Mel-Cepstrum and Regressive Coefficient. Also, we could get 74.3% recognition rate for expanded feature parameter, and 75.4% for applying acoustic feature. Since, the case of applying acoustic feature got better result than former method, we could make certain that suggested method is effective for connected digit recognition in korean.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.9C
• /
• pp.907-912
• /
• 2005

An efficient method for calculation of observation probability in CDHMM(Continous Density Hidden Markov Model) is proposed in this paper. the proposed algorithm, called FCOP(Fast Computation of Observation Probability), approximate obsewation probabilities in CDHMM by eliminating insignificant PDFs(Probability Density Functions) and reduces the computational load. When applied to a speech recognition system, the proposed FCOP algorithm can reduce the instruction cycles by $20\%-30\%$ and can also increase the recognition speed about $30\%$ while minimizing the loss in its recognition rate. When implemented on a practical cellular phone, the FCOP algorithm can increase its recognition speed about $30\%$ while suffering $0.2\%$ loss in recognition rate.

• 한국HCI학회:학술대회논문집
• /
• 2008.02c
• /
• pp.172-177
• /
• 2008

Biometrics is essential for person identification because of its uniqueness from each individuals. Face recognition technology has advantage over other biometrics because of its convenience and non-intrusive characteristics. In this paper, we will present a overview of face recognition technology including face detection, feature extraction, and face recognition system. For face detection, we will describe template based method and face component based approach. PCA and LDA approach will be discussed for feature extraction, and nearest neighbor classifiers -will be covered for matching. Large database and the standardized performance evaluation methodology is essential in order to support state-of-the-art face recognition system. Also, 3D based face recognition technology is the key solution for the pose, lighting and expression variations in many applications.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.8
• /
• pp.727-739
• /
• 2003

In this paper, we propose a generation method of regression classes for adaptation in the HM-Net (Hidden Markov Network) system. The MLLR (Maximum Likelihood Linear Regression) adaptation approach is applied to the HM-Net speech recognition system for expressing the characteristics of speaker effectively and the use of HM-Net in various tasks. For the state level sharing, the context domain state splitting of PDT-SSS (Phonetic Decision Tree-based Successive State Splitting) algorithm, which has the contextual and time domain clustering, is adopted. In each state of contextual domain, the desired phoneme classes are determined by splitting the context information (classes) including target speaker's speech data. The number of adaptation parameters, such as means and variances, is autonomously controlled by contextual domain state splitting of PDT-SSS, depending on the context information and the amount of adaptation utterances from a new speaker. The experiments are performed to verify the effectiveness of the proposed method on the KLE (The center for Korean Language Engineering) 452 data and YNU (Yeungnam Dniv) 200 data. The experimental results show that the accuracies of phone, word, and sentence recognition system increased by 34∼37%, 9%, and 20%, respectively, Compared with performance according to the length of adaptation utterances, the performance are also significantly improved even in short adaptation utterances. Therefore, we can argue that the proposed regression class method is well applied to HM-Net speech recognition system employing MLLR speaker adaptation.

• The Journal of the Acoustical Society of Korea
• /
• v.34 no.2
• /
• pp.171-176
• /
• 2015

We present a speaker verification method by extracting i-vectors based on dominant state information of Hidden Markov Model (HMM) - Universal Background Model (UBM). Ergodic HMM is used for estimating UBM so that various characteristic of individual speaker can be effectively classified. Unlike Gaussian Mixture Model(GMM)-UBM based speaker verification system, the proposed system obtains i-vectors corresponding to each HMM state. Among them, the i-vector for feature is selected by extracting it from the specific state containing dominant state information. Relevant experiments are conducted for validating the proposed system performance using the National Institute of Standards and Technology (NIST) 2008 Speaker Recognition Evaluation (SRE) database. As a result, 12 % improvement is attained in terms of equal error rate.

• Journal of the Institute of Convergence Signal Processing
• /
• v.2 no.4
• /
• pp.9-15
• /
• 2001

In this paper we investigate context dependent acoustic models to improve the performance of the Korean speech recognition . The algorithm are using the Korean phonological rules and decision tree, By Successive State Splitting(SSS) algorithm the Hidden Merkov Netwwork(HM-Net) which is an efficient representation of phoneme-context-dependent HMMs, can be generated automatically SSS is powerful technique to design topologies of tied-state HMMs but it doesn't treat unknown contexts in the training phoneme contexts environment adequately In addition it has some problem in the procedure of the contextual domain. In this paper we adopt a new state-clustering algorithm of SSS, called Phonetic Decision Tree-based SSS (PDT-SSS) which includes contexts splits based on the Korean phonological rules. This method combines advantages of both the decision tree clustering and SSS, and can generated highly accurate HM-Net that can express any contexts To verify the effectiveness of the adopted methods. the experiments are carried out using KLE 452 word database and YNU 200 sentence database. Through the Korean phoneme word and sentence recognition experiments. we proved that the new state-clustering algorithm produce better phoneme, word and continuous speech recognition accuracy than the conventional HMMs.