• Proceedings of the Acoustical Society of Korea Conference
• /
• autumn
• /
• pp.131-134
• /
• 2004

본 논문에서는 GMM(Gaussian Mixture Model)을 이용한 문맥독립 화자 검증 시스템을 구현한 후, arctan 함수를 이용한 정규화 방법을 사용하여 화자검증실험을 수행하였다. 특징파라미터로서는 선형예측방법을 이용한 켑스트럼 계수와 회귀계수를 사용하고 화자의 발성 변이를 고려하여 CMN(Cepstral Mean Normalization)을 적용하였다. 화자모델 생성을 위한 학습단에서는 화자발성의 음향학적 특징을 잘 표현할 수 있는 GMM(Gaussian Mixture Model)을 이용하였고 화자 검증단에서는 ML(Maximum Likelihood)을 이용하여 유사도를 계산하고 기존의 정규화 방법과 arctan 함수를 이용한 방법에 의해 정규화된 점수(score)와 미리 정해진 문턱값과 비교하여 검증하였다. 화자 검증 실험결과, arctan 함수를 부가한 방법이 기존의 방법보다 항상 향상된 EER을 나타냄을 확인할 수 있었다.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.8 no.4
• /
• pp.33-38
• /
• 2009

This paper proposes an automatic equalizer control method in automobile audio system. The proposed method discriminates the music segment from the consecutive real-time audio stream of the radio and the equalizer is controlled automatically according to the classified genre of the music segment. For enhancing the accuracy of the music genre classification in real-time, timbre feature and rhythm feature extracted from the consecutive audio stream is applied to GMM(Gaussian mixture model) classifier. The proposed method evaluates the performance of the music genre classification, which classified various audio segments segmented from the audio signal of the radio broadcast in automobile audio system into one of five music genres.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.1
• /
• pp.1-7
• /
• 2016

ADAS (Advanced Driver Assistance Systems) requires not only real-time robust lane detection, both straight and curved, but also predicting upcoming steering direction by detecting the curvature of lanes. In this paper, a curvature lane detection algorithm is proposed to enhance the accuracy and detection rate based on using inverse perspective images and Gaussian Mixture Model (GMM) to segment the lanes from the background under various illumination condition. To increase the speed and accuracy of the lane detection, this paper used template matching, RANSAC and proposed post processing method. Through experiments, it is validated that the proposed algorithm can detect both straight and curved lanes as well as predicting the upcoming direction with 92.95% of detection accuracy and 50fps speed.

• Journal of the Semiconductor & Display Technology
• /
• v.12 no.2
• /
• pp.67-72
• /
• 2013

Temperature is a critical parameter in yield improvement for wafer manufacturing. In chemical vapor deposition (CVD) equipment, crack defect in ceramic heater leads to yield reduction, however, there is no suitable ceramic heater fault detection system for conventional CVD equipment. This paper proposes a short-time zero-crossing rate based fault detection method for the ceramic heater in CVD equipment. The proposed method measures the output signal ($V_{pp}$) of RF filter and extracts the zero-crossing rate (ZCR) as feature vector. The extracted feature vectors have a discriminant power and Gaussian mixture model (GMM) based fault detection method can detect fault in ceramic heater. Experimental results, carried out by measured signals provided by a CVD equipment manufacturer, indicate that the proposed method detects effectively faults in various process conditions.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.2E
• /
• pp.68-75
• /
• 1994

In many applications of signal processing, we have to deal with densities which are highly non-Gaussian or which may have Gaussian shape in the middle but have potent deviations in the tails. To fight against these deviations, we consider a finite mixture distribution for the speech excitation. We utilize the EM algorithm for the estimation of speech parameters and their enhancement. Robust Kalman filtering is used in the enhancement process, and a detection/estimation technique is used for parameter estimation. Experimental results show that the proposed algorithm performs better in adverse SNR input conditions.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.3
• /
• pp.285-294
• /
• 2012

Using bearing measurement only, target motion state is not directly obtained so that TMA (Target Motion Analysis) is needed for this situation. TMA is a nonlinear estimation technique used in passive SONAR systems. Also it is the one of important techniques for underwater combat management systems. TMA can be divided to two parts: batch estimation and sequential estimation. It is preferable to use sequential estimation for reducing computational load as well as adaptively to target maneuvers, batch estimation is still required to attain target initial state vector for convergence of sequential estimation. Selection of batch time interval which depends on observability is critical in TMA performance. Batch estimation in general utilizes predetermined batch time interval. In this paper, we propose a new method called the BTIS (Batch Time Interval and Initial State Estimation). The proposed BTIS estimates target initial status and determines the batch time interval sequentially by using a bank of GMM-TS (Gaussian Mixture Measurement-Track Splitting) filters. The performance of the proposal method is verified by a Monte Carlo simulation study.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.482-486
• /
• 2008

본 논문에서는 하드 디스크 드라이브(Hard Disk Drive, HDD) 생산 공정 과정에서 발생할 수 있는 불량 HDD의 결함 분포에 대해서 패턴을 자동으로 분류해주는 기법을 제시한다. 이를 위해서 표준 패턴 클래스로 분류되어 있는 불량 HDD의 각 클래스의 확률 모델을 GMM(Gaussian Mixture Model)로 가정한다. 실험은 전문가에 의해 분류된 실제 HDD 결함 분포로부터 5가지의 특징 값들을 추출한 후, 결함 분포의 클래스를 표현할 수 있는 GMM의 파라미터(Parameter)를 학습한다. 각 모델의 파라미터를 추정하기 위해 EM(Expectation Maximization) 알고리즘을 사용한다. 학습된 GMM의 분류 테스트는 학습에 사용되지 않은 HDD 결함 분포에서 5가지의 특징 값을 입력 값으로 추정된 모델들의 파라미터 값에 의해 사후 확률을 구한다. 계산된 확률 값 중 가장 큰 값을 갖는 모델의 클래스를 표준 패턴 클래스로 분류한다. 그 결과 제시된 GMM을 이용한 HDD의 패턴 분류의 결과 96.1%의 정답률을 보여준다.

• Journal of the Institute of Convergence Signal Processing
• /
• v.17 no.2
• /
• pp.67-70
• /
• 2016

This paper discusses a graphic user interface(GUI) for the concealed target segmentation. The human subject hiding a metal gun is captured by the passive millimeter wave(MMW) imaging system. The imaging system operates on the regime of 8 mm wavelength. The MMW image is analyzed by the multi-level segmentation to segment and identify a concealed weapon under clothing. The histogram of the passive MMW image is modeled with the Gaussian mixture distribution. LBG vector quantization(VQ) and expectation and maximization(EM) algorithms are sequentially applied to segment the body and the object area. In the experiment, the GUI is implemented by the MFC(Microsoft Foundation Class) and the OpenCV(Computer Vision) libraries and tested in real-time showing the efficiency of the system.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.4
• /
• pp.163-168
• /
• 2005

In this paper, we propose a character-based summarization algorithm using speaker identification method from the dialog in video. First, we extract the dialog of shots containing characters' face and then, classify the scene according to actor/actress by performing speaker identification. The classifier is based on the GMM(Gaussian Mixture Model) using the 24 values of MFCC(Mel Frequency Cepstrum Coefficient). GMM is trained to recognize one actor/actress among four who are all trained by GMM. Our experiment result shows that GMM classifier obtains the error rate of 0.138 from our video data.

• Journal of Digital Convergence
• /
• v.13 no.2
• /
• pp.135-140
• /
• 2015

General CHMM vocabulary recognition system is model observation probability for vocabulary recognition of recognition rate's low. Used as the limiting unit is applied only to some problem in the phoneme model. Also, they have a problem that does not conform to the needs of the search range to meaning of the words in the vocabulary. Performs a phoneme recognition using GMM to improve these problems. We solve the problem according to the limited search words characterized by an improved k-means algorithm. Measure the effectiveness represented by the accuracy and reproducibility as compared to conventional system performance experiments. Performance test results accuracy is 83%p, and recall is 67%p.