• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.5
• /
• pp.85-91
• /
• 1989

In this paper, we propose a neural net system for speech recognition, which is composed of two neural networks. Firstly the self-supervised BP(Back Propagation) network generates the distributed concept corresponding to the activity pattern in the hidden units. And then the self-organizing neural network forms a concept map which directly displays the similarity relations between concepts. By doing the above, the difficulty in learning the conventional BP network is solved and the weak side of BP falling into a pattern matcher is gone, while the strong point of generating the various internal representations is used. And we have obtained the concept map which is more orderly than the Kohonen's SOFM. The proposed neural net system needs not any special preprocessing and has a self-learning ability.

• International Journal of Computer Science & Network Security
• /
• v.21 no.8
• /
• pp.127-136
• /
• 2021

Real-time human recognition is a challenging task, as the images are captured in an unconstrained environment with different poses, makeups, and styles. This limitation is addressed by generating several facial images with poses, makeup, and styles with a single reference image of a person using Generative Adversarial Networks (GAN). In this paper, we propose deep learning-based human recognition using integration of GAN and Spatial Domain Techniques. A novel concept of human recognition based on face depiction approach by generating several dissimilar face images from single reference face image using Domain Transfer Generative Adversarial Networks (DT-GAN) combined with feature extraction techniques such as Local Binary Pattern (LBP) and Histogram is deliberated. The Euclidean Distance (ED) is used in the matching section for comparison of features to test the performance of the method. A database of millions of people with a single reference face image per person, instead of multiple reference face images, is created and saved on the centralized server, which helps to reduce memory load on the centralized server. It is noticed that the recognition accuracy is 100% for smaller size datasets and a little less accuracy for larger size datasets and also, results are compared with present methods to show the superiority of proposed method.

• Cross-Cultural Studies
• /
• v.25
• /
• pp.337-362
• /
• 2011

This study focused on difference of the nation's concept between Ko un's Baekdusan and Lee uk's Gohyangsaramdul, Pungungi. These works are epics restructure nation's history. A epic's story provides framework of recognition to social members. An individual and community accept their story and then stories construct pesonal identity and community's identity. So we can say a epic configurates national identity by story nation history and nation territory. The nation's concept is understood steadfast and very pure as like a blood relationship in Korea. This is aspects of Korean nationalism. But the Nation is modern, social and historical concept. That is different from ethnic identity. This way throws open the door to analyze nation identity. Ko un's Baekdusan narrates permanence and sacralization of the nation for emphasizing the unification of North Korea and South Korea. Baekdusan expresses the social desire of Korea in the 1980s. In comparison, Lee uk's Gohyangsaramdul representate ambivalent attitude. One is a position as a settler and the other is a new master of Yanbian Korean Autonomous Prefecture. So Gohyangsaramdul narrates and remembers their motherland Chosun. But Pungungi exclude recognition of Chosun as motherland. This work's narration focuses on association with struggle of classes and anti-Japanese Movement during the Japanese colonial period. Because these events are able to unity Korean and Chines. Three works deal with same history and same background, but those show defferent recognition about the Nation. Because each society has different social desire and expect different future. The present desire and future prospect construct nation identity.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11b
• /
• pp.762-766
• /
• 2002

This paper describes the emotion recognition algorithm using HMM(Hidden Markov Model) method. The relation between the mechanic system and the human has just been unilateral so far. This is the why people don't want to get familiar with multi-service robots of today. If the function of the emotion recognition is granted to the robot system, the concept of the mechanic part will be changed a lot. Pitch and Energy extracted from the human speech are good and important factors to classify the each emotion (neutral, happy, sad and angry etc.), which are called prosodic features. HMM is the powerful and effective theory among several methods to construct the statistical model with characteristic vector which is made up with the mixture of prosodic features

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2002.11a
• /
• pp.375.2-375
• /
• 2002

This paper describes the emotion recognition algorithm using HMM(Hidden Markov Model) method. The relation between the mechanic system and the human has just been unilateral so far This is the why people don't want to get familiar with multi-service robots. If the function of the emotion recognition is granted to the robot system, the concept of the mechanic part will be changed a lot. (omitted)

• 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].

• Phonetics and Speech Sciences
• /
• v.9 no.2
• /
• pp.103-110
• /
• 2017

The pole filtering concept has been successfully applied to cepstral feature normalization techniques for noise-robust speech recognition. In this paper, it is proposed to apply the pole filtering selectively only to the speech intervals, in order to further improve the recognition performance for short utterances in noisy environments. Experimental results on AURORA 2 task with clean-condition training show that the proposed selectively pole-filtered cepstral mean normalization (SPFCMN) and selectively pole-filtered cepstral mean and variance normalization (SPFCMVN) yield error rate reduction of 38.6% and 45.8%, respectively, compared to the baseline system.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.2
• /
• pp.96-99
• /
• 2020

According to brilliant development of smart devices, many related services are being devised. And, almost every service is designed to provide user-centric services based on personal information. In this situation, to prevent unintentional leakage of personal information is essential. Conventionally, ID and Password system is used for the user authentication. This is a convenient method, but it has a vulnerability that can cause problems due to information leakage. To overcome these problem, many methods related to face recognition is being researched. Through this paper, we investigated the trend of user authentication through biometrics and a representative model for face recognition techniques. One is DeepFace of FaceBook and another is FaceNet of Google. Each model is based on the concept of Deep Learning and Distance Metric Learning, respectively. And also, they are based on Convolutional Neural Network (CNN) model. In the future, further research is needed on the equipment configuration requirements for practical applications and ways to provide actual personalized services.

• Journal of Information Processing Systems
• /
• v.8 no.3
• /
• pp.445-458
• /
• 2012

Image feature extraction is one of the basic works for biometric analysis. This paper presents the novel concept of application of ridgelets for iris recognition systems. Ridgelet transforms are the combination of Radon transforms and Wavelet transforms. They are suitable for extracting the abundantly present textural data that is in an iris. The technique proposed here uses the ridgelets to form an iris signature and to represent the iris. This paper contributes towards creating an improved iris recognition system. There is a reduction in the feature vector size, which is 1X4 in size. The False Acceptance Rate (FAR) and False Rejection Rate (FRR) were also reduced and the accuracy increased. The proposed method also avoids the iris normalization process that is traditionally used in iris recognition systems. Experimental results indicate that the proposed method achieves an accuracy of 99.82%, 0.1309% FAR, and 0.0434% FRR.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.719-724
• /
• 1998

This paper presents a systematic developement of a formal approach to inference in approximate reasoning. We introduce some measures of similarity and discuss their properties. Using the concept of similarity index we formulate two methods for inferring from vague knowledge. In order to illustrate the effectiveness of the proposed technique we use it to develop a vowel recognition system.