• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.4
• /
• pp.964-969
• /
• 2008

This paper proposes a HMM-based recognition method using DMSVQ(Dynamic Multi-Section Vector Quantization) codebook by DMS(Dynamic Multi-Section) model and fuzzy concept, as a study for speaker- independent speech recognition. In this proposed recognition method, training data are divided into several dynamic section and multi-observation sequences which are given proper probabilities by fuzzy rule according to order of short distance from DMSVQ codebook per each section are obtained. Thereafter, the HMM using this multi-observation sequences is generated, and in case of recognition, a word that has the most highest probability is selected as a recognized word. Other experiments to compare with the results of recognition experiments using proposed method are implemented as a data by the various conventional recognition methods under the equivalent environment. Through the experiment results, it is proved that the proposed method in this study is superior to the conventional recognition methods.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2012.05a
• /
• pp.371-373
• /
• 2012

본 논문에서는 컬러 영상 기반에서 배경에 강인한 피부 영역 검출 기법을 제안하고 손 인식기법을 활용한 응용프로그램을 제안한다. 코드북 모델[1]을 이용하여 배경/전경을 분리하고, 분리된 전경에서 피부색정보를 이용하여 관심영역을 도출한다. 피부 영역을 검출하기 위한 단계에서는 YCbCr, HSV, LUV 색상 모델의 혼합하여 피부색 후보 영역에 대한 임계구간을 통해 강인한 피부 영역을 분할한다. 분할된 영역을 관심영역으로 설정하고 Kalman filter를 이용하여 영역을 추적한다. 결과적으로 복잡하고 고정된 배경에서 조명에 강인한 피부 영역 분할 및 추적이 가능하며 이를 응용한 사용자 인터페이스로 사용될 수 있다.

• Journal of the Korea Computer Industry Society
• /
• v.5 no.4
• /
• pp.491-502
• /
• 2004

In this paper, we propose a HMM model using FSVQ(First Section VQ), fuzzy theory and doubly spectral feature, as study on the isolated word recognition system of speaker-independent. In the proposed paper, LPC cepstrum coefficients and regression coefficients of LPC cepstrum as doubly spectral feature be used. And, training data are divided several section and first section is generated codebook of VQ, and then is obtained multi-observation sequences by order of large propabilistic values based on fuzzy nile from the codebook of the first section. Thereafter, this observation sequences of first section is trained and is recognized a word to be obtained highest probaility by same concept. Besides the speech recognition experiments of proposed method, we experiment the other methods under the equivalent environment of data and conditions. In the whole experiment, it is proved that the proposed method is superior to the others in recognition rate.

• The Journal of the Acoustical Society of Korea
• /
• v.21 no.7
• /
• pp.641-647
• /
• 2002

In this paper, we propose the reduction method of the number of parameters in the segmental-feature HMM using trend quantization method. The proposed method shares the trend information of the polynomial trajectories by quantization. The trajectory is obtained by the sequence of feature vectors of speech signals and can be divided by trend and location information. The trend indicates the variation of consequent frame features, while the location points to the positional difference of the trajectories. Since the trend occupies the large portion of SFHMM, if the trend is shared, the number of parameters maybe decreases. To exploit the proposed system the experiments are performed on TIMIT corpus. The experimental results show that the performance of the proposed system is roughly similar to that of previous system. Therefore, the proposed system can be considered one of parameter reduction method.

• Journal of Digital Contents Society
• /
• v.18 no.2
• /
• pp.383-392
• /
• 2017

This paper introduces a real-time 3D model generation system that can process in real time from multi-view image acquisition to image-based 3D model generation. This system describes how to collect, transmit, and manage the HD images input from 18 cameras and explain the background separation and smooth 3D volume model generation process. This paper proposes a new distributed data transmission and reception method for real-time processing of HD images input from 18 cameras. In addition, we describe a codebook-based background separating algorithm and a modified marching cube algorithm using perspective difference interpolation to generate smooth 3D models from multi-view images. The system is currently being built with a throughput rate of 30 frames per second.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.46 no.9
• /
• pp.1-7
• /
• 2009

LTE-A (long term evolution advanced) uplink selected SC-FDMA (single carrier frequency division multiple access) to maintain low PAPR for a low price and tiny terminal. Recently, the application of codebook-based preceding to LIE-A uplink is discussed. This paper shows that PAPR can be increased when various preceding schems are applied to the SC-FDMA as an LTE-A uplink. When, considering nonlinear power amplifier model to the transmitter, BER performances of preceded schemes degrade. But equal gain transmission scheme does show very low PAPR. So the link-level performance of EGT is superior to those of any other preceding schemes. Computer simulations also confirm the anticipated link-level performances.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.500-510
• /
• 2023

Passive sonar signals mainly contain both normal and abnormal signals. The abnormal signals mixed with normal signals are primarily detected using an AutoEncoder (AE) that learns only normal signals. However, existing AEs may perform inaccurate detection by reconstructing distorted normal signals from mixed signal. To address these limitations, we propose an abnormal signal detection model based on a Recurrent Neural Network (RNN) and vector quantization. The proposed model generates a codebook representing the learned latent vectors and detects abnormal signals more accurately through the proposed search process of code vectors. In experiments using publicly available underwater acoustic data, the AE and Variational AutoEncoder (VAE) using the proposed method showed at least a 2.4 % improvement in the detection performance and at least a 9.2 % improvement in the extraction performance for abnormal signals than the existing models.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.7
• /
• pp.312-318
• /
• 2006

The conventional lip-synch system has a two-step process, speech segmentation and recognition. However, the difficulty of speech segmentation procedure and the inaccuracy of training data set due to the segmentation lead to a significant Performance degradation in the system. To cope with that, the connected vowel recognition method using Head-Body-Tail (HBT) model is proposed. The HBT model which is appropriate for handling relatively small sized vocabulary tasks reflects co-articulation effect efficiently. Moreover the 7 vowels are merged into 3 classes having similar lip shape while the system is optimized by employing a class dependent SCHMM structure. Additionally in both end sides of each word which has large variations, 8 components Gaussian mixture model is directly used to improve the ability of representation. Though the proposed method reveals similar performance with respect to the CHMM based on the HBT structure. the number of parameters is reduced by 33.92%. This reduction makes it a computationally efficient method enabling real time operation.

• Journal of Internet Computing and Services
• /
• v.15 no.1
• /
• pp.125-134
• /
• 2014

As the social media which was simple communication media is activated on account of twitter and facebook, it's usability and importance are growing recently. Although many companies are making full use of its the capacity of information diffusion for marketing, the adverse effects of this capacity are growing. Because social network is formed and communicates based on friendships and relationships, the spreading speed of the spam and mal-ware is very swift. In this paper, we draw parameters affecting malicious data diffusion in social network environment, and compare and analyze the diffusion capacity of each parameters by propagation experiment with XSS Worm and Koobface Worm. In addition, we discuss the structural characteristics of social network environment and then proposed malicious data propagation model based on parameters affecting information diffusion. n this paper, we made up BA and HK models based on SI model, dynamic model, to conduct the experiments, and as a result of the experiments it was proved that parameters which effect on propagation of XSS Worm and Koobface Worm are clustering coefficient and closeness centrality.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.8
• /
• pp.67-80
• /
• 2017

This paper presents a hole-filling method using extrapolated spatio-temporal background information to obtain a synthesized view. A new temporal background model using non-overlapped patch based background codebook is introduced to extrapolate temporal background information In addition, a depth-map driven spatial local background estimation is addressed to define spatial background constraints that represent the lower and upper bounds of a background candidate. Background holes are filled by comparing the similarities between the temporal background information and the spatial background constraints. Additionally, a depth map-based ghost removal filter is described to solve the problem of the non-fit between a color image and the corresponding depth map of a virtual view after 3-D warping. Finally, an inpainting is applied to fill in the remaining holes with the priority function that includes a new depth term. The experimental results demonstrated that the proposed method led to results that promised subjective and objective improvement over the state-of-the-art methods.