http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
이수길, 송정영 배재대학교 공학연구소 2016 공학논문집 Vol.18 No.1
본 논문은 한국어 음성의 음소분리에 관한 연구이다. 음성인식에 있어서 음성을 음소단위로 인식하는 방법은 가장 효과적인 방법이다. 그러나 음성을 음소단위로 분리하는 것은 발음의 변화가 너무 다양하기 때문에 잘 적용되지 못하고 있다. 따라서 본 연구에서는 훈민정음의 음운체계를 기초로 하여 한국어의 음소체계를 정리하고 음성을 음소단위로 분리하고자 한다. 본 연구에서는 음소를 주파수 영역과 멜대역 그리고 멜켑스트럼의 변화를 관찰하여 각 음소들이 가지고 있는 특징을 찾아내고 분리의 규칙을 정리하여 효과적인 음성인식 방법이 될 수 있는 한국어 음소분리 체계를 정립하고자 한다. It is generally known that accurate segmentation is very necessary for both an individual word and continuous utterances in speech recognition. It is also commonly known that techniques are now being developed to classify the voiced and the unvoiced, also classifying the plosives and the fricatives. The method for accurate recognition of the phonemes isn't yet scientifically established. Therefore, in this study we analyze the Korean language, using the classification of "Hunminjeongeum" and contemporary phonetics, with the frequency band, Mel band and Mel Cepstrum, we extract notable features of the phonemes from Korean speech and segment speech by the unit of the phonemes to normalize them. Finally, through the analysis and verification, we intend to set up Phonemic Segmentation System that will make us able to adapt it to both an individual word and continuous utterances.
이수길, 송정영 배재대학교 공학연구소 2014 공학논문집 Vol.16 No.1
It is generally known that accurate segmentation is very necessary for both an individual word and continuous utterances in speech recognition. It is also commonly known that techniques are now being developed to classify the voiced and the unvoiced, also classifying the plosives and the fricatives. The method for accurate recognition of the phonemes isn't yet scientifically established. Therefore, in this study we analyze the Korean language, using the classification of "Hunminjeongeum" and contemporary phonetics, with the frequency band, Mel band and Mel Cepstrum, we extract notable features of the phonemes from Korean speech and segment speech by the unit of the phonemes to normalize them. Finally, through the analysis and verification, we intend to set up Phonemic Segmentation System that will make us able to adapt it to both an individual word and continuous utterances.
근적외투과분석법에 의한 현미의 Acid value 정량분석
서자영,이수정,신명곤 우송대학교 산업연구소 2000 산업연구 Vol.2 No.1
Infratec 1229 analyzer in determining acid value of whole grain brown rice was applied. The standard error of calibration(SEC) and R2 of acid value were 2.571 and 0.649 respectively. The results showed that acid value of brown rice could be partly analyzed by Near-infrared transmittance spectroscopy.
도로 노면의 형상과 강우의 임계 지속시간을 고려한 적정 우수 유출량 산정 및 영향분석
이종태,김영란,김갑수,윤세의,박영민 대한상하수도학회 2003 상하수도학회지 Vol.17 No.2
When calculating the storm runoff from road surface, it is recommendable to introduce the critical duration of rainfall by means of the RUNOFF (SWMM) model, or the Rational method with the travel time values of the kinematic wave' or Kerby's equation modified by multiplying the correction factor of 2.3 or 1.1, respectively. But the travel time of 5-10 minutes suggested in the Guide Manual for Sewer Design is too long to use for calculating road surface runoff. The peak runoff rate increases as the road sectional slope increases, whereas it shows the opposite results for an increase in the longitudinal slope. Also, the effects of the width and length of the road on the surface runoff rates increases greatly, as their values increase.
An Intelligent Multi-Sensor Surveillance System for Elderly Care
Sou-Young Jin,Young-Seob Jeong,Chankyu Park,KyoJoong Oh,Ho-Jin Choi 한국산학기술학회 2012 SmartCR Vol.2 No.4
This paper is an overview of our on-going project that proposes a monitoring system based on various sensors to detect risky situations for the elderly. From the standpoint of the end-user, a video surveillance system equipped with many other sensors can relieve caregivers from the need to keep a vigilant eye on each patient’s movements, while such technology can be effectively used for monitoring elderly people with dementia. Since a camera surveillance system has limits to classify complex human actions, this project aims to design an intelligent healthcare surveillance system, which extends the conventional automated video surveillance system with various additional sensors, to improve the performance of surveillance. The main contributions of our proposed system will be to: (i) minimize human intervention; (ii) detect more complex activities and situations using various sensors and improved sensor fusion techniques; and (iii) design a novel classifier that identifies risky situations with the collected information.
Non-Simultaneous Sampling Deactivation during the Parameter Approximation of a Topic Model
( Young-seob Jeong ),( Sou-young Jin ),( Ho-jin Choi ) 한국인터넷정보학회 2013 KSII Transactions on Internet and Information Syst Vol.7 No.1
Since Probabilistic Latent Semantic Analysis (PLSA) and Latent Dirichlet Allocation (LDA) were introduced, many revised or extended topic models have appeared. Due to the intractable likelihood of these models, training any topic model requires to use some approximation algorithm such as variational approximation, Laplace approximation, or Markov chain Monte Carlo (MCMC). Although these approximation algorithms perform well, training a topic model is still computationally expensive given the large amount of data it requires. In this paper, we propose a new method, called non-simultaneous sampling deactivation, for efficient approximation of parameters in a topic model. While each random variable is normally sampled or obtained by a single predefined burn-in period in the traditional approximation algorithms, our new method is based on the observation that the random variable nodes in one topic model have all different periods of convergence. During the iterative approximation process, the proposed method allows each random variable node to be terminated or deactivated when it is converged. Therefore, compared to the traditional approximation ways in which usually every node is deactivated concurrently, the proposed method achieves the inference efficiency in terms of time and memory. We do not propose a new approximation algorithm, but a new process applicable to the existing approximation algorithms. Through experiments, we show the time and memory efficiency of the method, and discuss about the tradeoff between the efficiency of the approximation process and the parameter consistency.
Optical and Structural Analysis of Zinc Oxysulfide Digital Alloys Grown by Atomic Layer Deposition
Sou Young Yu,Mostafa A Hassan,Muhammad Ali Johar,Sang-Wan Ryu 한국물리학회 2018 THE JOURNAL OF THE KOREAN PHYSICAL SOCIETY Vol.73 No.5
We investigated the optical and structural properties of ZnOS digital alloy grown on Si by atomic layer deposition. The refractive index and extinction coecient were evaluated using spectroscopic ellipsometry. ZnOS alloy film shows a strong absorption tail extended to the below band gap regime, which is attributed to a high density of band tail states formed within the band gap owing to the amorphous crystallinity. The ZnOS alloy exhibits a large Urbach energy of 210 - 540 meV. After high-temperature annealing, the band tail states are reduced with a decrease in lattice disorder, which is confirmed by enhanced X-ray diffraction peaks.
A Study on the Absorption of Formaldehyde by Various Capets
Sou, Bo Young,Lee, Eun Woo 영남이공대학 1994 論文集 Vol.23 No.-
각종 카펫이 공기중의 formaldehyde를 얼마나 감소시킬 수 있는 지를 알고자하여 소정의 밀폐된 용기를 오염시켜 각종 카펫에 의한 흡착실험을 하여 실내 공기의 정화 능력을 알고져 하였다. 실험결과 양모카펫이 나일론 카펫보다 formaldehyde의 흡착능력이 우수하였으며 이는 양모 카펫이 실내 공기중의 formaldehyde를 감소 시킬 수 있는 능력이 탁월하다는 것을 알 수 있다.