• Proceedings of the Korean Society for Information Management Conference
• /
• 1997.08a
• /
• pp.17-24
• /
• 1997

조사에 따르면 한글 문서에서 사용되는 단어 중 외래어 또는 영어가 포함된 단어가 약 26%정도를 차지하고 있으며, 이는 정보검색의 중요 색인어로 사용된다(권윤형 1996). 그러나 이들 단어들은 서로 같은 단어인데도 영어로 표기되기도 하고 이형의 외래어들로 표기되기도 하여, 정보검색의 효율을 떨어뜨리고 있다. 본 논문에서는 영어 단어와 그에 대응되어 표기되는 외래어들을 찾기 위한 한 단계로서, 영어를 한글로 음차(transliteration)하여 자동표기하는 통계적 모델을 제안하고 실험한다. 제안된 모델은 통계적 기계번역 방식과 그의 한 방법인 문서 정렬(text alignment) 방식에 근거하고 있다. 특히 이 모델에서는 효과적으로 발음의 단위를 분리한 다음 정렬을 하여. 전체적인 계산량을 줄이고 성능도 향상시켰다. 음차표기는 피봇방식과 직접방식의 두가지로 구현하였다. 피봇방식은 영어에서 발음을 생성한 후, 그 발음을 다시 한글로 표기하는 방식이고, 직접방식은 직접 영어 단어에서 한글 표기로 포기하는 방식이다. 두 방식을 제안된 모델을 이용하여 비교 테스트한 결과 직접방식이 보다 정확하게 표준 외래어로 표기하였다.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.4 s.304
• /
• pp.103-110
• /
• 2005

Speech Database is one of the most important part of Text-to-speech(TTS) system Especially, the embedded TTS system needs more small size of database than that of the server TTS system So, the compression and statistical reduction or database is a very important factor in the embedded TTS system But this compression and statistical reduction of database always rise a loss of quality of the synthesised speech. In this paper, we propose a method of constructing database for high quality embedded TTS system and verify the quality of synthesised speech with MOS(Mean Opinion Score) test.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.6
• /
• pp.324-329
• /
• 2011

In this paper, we propose a novel approach to improve the performance of a statistical model-based voice activity detection (VAD) which is based on the conditional maximum a posteriori (CMAP) with deviation. In our approach, the VAD decision rule is expressed as the geometric mean of likelihood ratios (LRs) based on adapted threshold according to the speech presence probability conditioned on both the speech activity decisions and spectral deviation in the pervious frame. Experimental results show that the proposed approach yields better results compared to the CMAP-based VAD using the LR test.

• The Journal of the Acoustical Society of Korea
• /
• v.26 no.5
• /
• pp.194-198
• /
• 2007

In this paper, we apply a discriminative weight training to a statistical model-based voice activity detection(VAD). In our approach, the VAD decision rule is expressed as the geometric mean of optimally weighted likelihood ratios(LRs) based on a minimum classification error(MCE) method which is different from the previous works in that different weights are assigned to each frequency bin which is considered more realistic. According to the experimental results, the proposed approach is found to be effective for the statistical model-based VAD using the LR test.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 1994.10a
• /
• pp.126-131
• /
• 1994

본 연구에서는 굽힘파(bending wave)의 전달만 고려하였는데 실제로는 보 및 비틀림 모드도 존재하나 고주파수 대역에서는 굽힘모드가 지배적이며 소음의 발생도 굽힘모드에 의해 주로 발생하므로 보 및 비틀림모드의 생략이 큰 오차를 가져오지는 않는다. 테스트 모델에 대해 실험을 수행하여 결과를 비교하였다. 또한 구조물의 고주파수 진동소음 해석방법으로 널리 쓰이는 통계적 에너지 해석법(SEA)을 이용한 결과와 비교하였다.

• Journal of KIISE:Software and Applications
• /
• v.41 no.8
• /
• pp.533-544
• /
• 2014

The hardware-based software has been loaded in almost all industrial fields including the embedded system field. As it is increasingly important to control product quality, the more businesses are expending great quality cost. However, most domestic corporations in Korea are bent on spending more money solving problems caused by poor quality rather than prevention of quality loss cost. Therefore, it's time to improve to use quality prevention cost efficiently. As for this, there has been a growing interest in controlling quantitative quality, but the managing activities for quantitative quality require a high maturity process, belonging to Level 4 and 5. So it is necessary that statistical quality control activities should be fulfilled. This study introduces various measures to build up quality control among the process areas of TMMi Level 5 to help establish the high maturity test processes of statistical quality control.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.712-716
• /
• 2008

In this paper, we introduce a way to generate and control the serial music using stochastical tools. A serialism, which is one of composition techniques in the 20th century modern music, is composed using uniformly distributed notes or durations. To conserve this property, we design the optimization process to generate the random numbers which can be used to compose the serial music. The optimization are designed using chi-square test and auto-correlation test. User can also apply the additional constraint to the objective function for controlling the serial music. Using the our method, we can compose and control the traditional serial music automatically.

• Journal of Advanced Navigation Technology
• /
• v.15 no.1
• /
• pp.18-24
• /
• 2011

This paper proposes fault diagnosis system which is able to diagnose the fault from present operating condition by analyzing monitored signals with present ship monitoring system without additional sensors. For this all kinds of ship's engine room monitored data are classified with combustion subsystem, heat exchange subsystem and electric motor and pump subsystem by analyzing ship's operation data. To extract dynamic characteristics of these subsystems, log book data of container ship of H shipping company are used.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.45 no.4
• /
• pp.100-106
• /
• 2008

In this paper we apply a discriminative weight training employing power spectral flatness measure (PSFM) to a statistical model-based voice activity detection (VAD) in various noise environments. In our approach, the VAD decision rule is expressed as the geometric mean of optimally weighted likelihood ratio test (LRT) based on a minimum classification error (MCE) method which is different from the previous works in th at different weights are assigned to each frequency bin and noise environments depending on PSFM. According to the experimental results, the proposed approach is found to be effective for the statistical model-based VAD using the LRT.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.4
• /
• pp.443-450
• /
• 2007

In this paper, we propose a novel threshold selection method based on statistical information on gray-levels of given images and interval-valued fuzzy sets. In the proposed threshold selection method, the interval-valued fuzzy set is used to represent more definitely the relationship between a pixel and its belonging region, that is, the object and the background. Also the statistical information on gray-level is used to determine the rules and partitions of interval-valued fuzzy sets. To show the validity of the proposed method, we compared the performance of the proposed with those of conventional methods such as Otsu's method, Huang and Wang's method applied to 5 test images with various types of histograms.