• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.7
• /
• pp.119-124
• /
• 2015

Speech enhancement has been required as a preprocessor for a noise robust speech recognition system. Codebook-based Speech Enhancement (CBSE) is highly robust in nonstationary noise environments compared with conventional noise estimation algorithms. However, its performance is severely degraded for the codevector combinations that have lower correlation with the input signal since CBSE depends on the trained codebook information. To overcome this problem, only the reliable codevector combinations are selected to be used to remove the codevector combinations that have lower correlation with input signal. The proposed method produces the improved performance compared to the conventional CBSE in terms of Log-Spectral Distortion (LSD) and Perceptual Evaluation of Speech Quality (PESQ).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.10B
• /
• pp.1428-1435
• /
• 2001

본 논문에서는 이미지 데이터의 저작권 보호를 위해 영상변형, JPEG 손실 압축 및 임펄스 잡음에 효과적인 새로운 DM/SS (Direct Matrix/Spread Spectrum) 이미지 워터마킹 기법을 제안한다. 제안하는 기법은 워터마크 영상을 저작권자의 개인 ID (IDentification)로 확산시킨 다음, 원 영상에 삽입하고 역확산시켜 복원하는 방법이다. 원터마크 영상은 2진 영상을 사용하고, 워터마크 시스템에서 요구되는 비가시성과 외부 공격에 대한 워터마크의 강인성을 확인하기 위하여 PSNR (Peak Signal to Noise Ratio)과 워터마크 영상의 복원율 (reconstructive rate)을 구한다. 실험 결과, 워터마크가 삽입된 영상의 PSNR은 93.75 dB로 화질저하가 거의 없었고, 확산 이득으로 인하여 32$\times$32 워터마크 영상이 삽입된 영상에서 우수한 워터마크 영상의 복원율을 얻는다는 것을 보인다. 영상변형 및 JPEG 손실 압축 하에서도 우수한 워터마크 복원 결과를 보였고, 임펄스 잡음이 첨가된 영상의 PSNR이 5.54 dB인 경우에도 효과적으로 워터마크 영상을 복원할 수 있다는 것을 알 수 있었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.8C
• /
• pp.516-521
• /
• 2011

In this paper, a nonlinear algorithm that maximizes zero-error probability (MZEP) with decision feedback (DF) is proposed to counteract both of severely distorted multi-path fading effect and impulsive noise. The proposed MZEP-DF algorithm has shown the immunity to impulsive noise and the ability of the feedback filter section to cancel the remaining intersymbol interference as well. Compared with the linear MZEP algorithm, it yields above 10 dB enhancement of steady state MSE performance in severely distorted multipath fading channels with impulse noise where the least mean square (LMS) algorithm does not converge below -3dB of MSE.

• Journal of Internet Computing and Services
• /
• v.17 no.3
• /
• pp.19-24
• /
• 2016

The minimum error entropy (MEE) algorithm is known to be superior in impulsive noise environment. In this paper, the optimum solutions and properties of the MEE algorithm are studied in regard to the robustness against impulsive noise. From the analysis of the behavior of optimum weight and factors related with mitigation of influence from large errors, it is revealed that the magnitude controlled input entropy plays the main role of keeping optimum weight of MEE undisturbed from impulsive noise. In the simulation, the optimum weight of MEE is shown to be the same as that of MSE criterion.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.1
• /
• pp.19-24
• /
• 2007

In this paper, we propose a tuning method of PID-PD controller to satisfy design specifications in frequency domain as well as time domain. The proposed tuning method of PID-PD controller consists of the convex set of PID and PI-PD controller. PID-PD controller controls the closed-loop response to be located between the step responses, and Bode magnitudes of closed-loop transfer functions controlled by PID and PI-PD controller. The controller is designed by the optimum tuning method to minimize the proposed specific cost function subject to sensor noise insensitivity and robust stability. Its effectiveness is examined by the case study and analysis.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.6
• /
• pp.95-101
• /
• 2009

Among the adaptive noise cancellers (ANC), the least mean square (LMS) algorithm has probably become the most popular algorithm because of its robustness, good tracking properties, and simplicity of implementation. However, it has non-uniform convergence and a trade-off between the rate of convergence and excess mean square error (EMSE). To overcome these shortcomings, a number of variable step size least mean square (VSSLMS) algorithms have been researched for years. These LMS algorithms use a complex variable step method approach for rapid convergence but need high computational complexity. A variable step approach can impair the simplicity and robustness of the LMS algorithm. The proposed instantaneous gain control (IGC) algorithm uses the instantaneous gain value of the original signal and the noise signal. As a result, the IGC algorithm can reduce computational complexity and maintain better performance.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.10
• /
• pp.887-895
• /
• 2014

Drowsy driving is a large proportion of the total car accidents. For this reason, drowsiness detection and warning system for drivers has recently become a very important issue. Monitoring physiological signals provides the possibility of detecting features of drowsiness and fatigue of drivers. Many researches have been published that to measure electroencephalogram(EEG) signals is the effective way in order to be aware of fatigue and drowsiness of drivers. The aim of this study is to extract drowsiness-related features from a set of EEG signals and to classify the features into three states: alertness, transition, and drowsiness. This paper proposes a drowsiness detection system using errors-in-variables(EIV) for extraction of feature vectors and multilayer perceptron (MLP) for classification. The proposed method evaluates robustness for noise and compares to the previous one using linear predictive coding (LPC) combined with MLP. From evaluation results, we conclude that the proposed scheme outperforms the previous one in the low signal-to-noise ratio regime.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.2
• /
• pp.137-142
• /
• 2010

Although multi-model speech recognizer has been shown to be quite successful in noisy speech recognition, the results were based on general speech front-ends which do not take into account noise adaptation techniques. In this paper, for the accurate evaluation of the multi-model based speech recognizer, we adopted a quite noise-robust speech front-end, AFE, which was proposed by the ETSI for the noisy DSR environment. For the performance comparison, the MTR which is known to give good results in the DSR environment has been used. Also, we modified the structure of the multi-model based speech recognizer to improve the recognition performance. N reference HMMs which are most similar to the input noisy speech are used as the acoustic models for recognition to cope with the errors in the selection of the reference HMMs and the noise signal variability. In addition, multiple SNR levels are used to train each of the reference HMMs to improve the robustness of the acoustic models. From the experimental results on the Aurora 2 databases, we could see better recognition rates using the modified multi-model based speech recognizer compared with the previous method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.5A
• /
• pp.298-304
• /
• 2012

In this paper, we propose robust estimators for the frequency offset of orthogonal frequency division multiplexing in non-Gaussian noise environments. We first propose a maximum-likelihood (ML) estimator in non-Gaussian noise modeled as a complex isotropic Cauchy process, and then, we present a simpler suboptimal estimator based on the ML estimator. From numerical results, it is demonstrated that the proposed estimators not only outperform the conventional estimators, but also have a robustness in non-Gaussian noise environments.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.06e
• /
• pp.381-384
• /
• 1998

본 논문은 주행중인 자동차 환경에서 운전자의 안전성 및 편의성의 동시 확보를 위하여, 보조적인 스위치 조작없이 상시 음성의 입, 출력이 가능하도록 한다. 이때 잡음에 강인한 threshold 값을 구하기 위하여, 일정한 시간마다 기준 에너지와 영교차율(Zero Crossing Rate)을 변경하며, 밴드패스 필터(bandpass filter)를 이용하여 1차, 2차로 나누어 실시간 상태에서 자동으로, 정확하게 끝점검출(End Point Detection)을 처리한다. 기준패턴(reference pattern)은 DMS(Dynamic Multi-Section)을 사용하며, 화자의 변별력을 높이기 위하여 2개의 모델사용을 제안한다. 또한 주행중인 차량의 잡음환경에 강인하기 위하여 일반주행(80km/h 이내), 고속주행(80km/h 이상)등으로 나누며 차량의 가변잡음 크기에 따라 자동으로 선택하도록 한다. 음성의 특징 벡터와 인식 알고리즘은 PLP 13차와 One-Stage Dynamic Programming (OSDP)를 이용한다. 실험결과, 자주 사용되는 차량 편의장치 제어명령 33개에 대하여 중부, 영동 고속도로(시속 80Km/h 이상)에서 화자독립 89.75%, 화자종속 90.08%의 인식율을 구하였으며, 경부 고속도로에서는 화자독립 92.29%, 화자종속 92.42%의 인식율을 구하였다. 그리고 저속 주행중인 자동차 환경(80km/h 이내, 시멘트, 아스팔트 등의 서울시내 및 시외독립)에서는 화자독립 92.89%, 화자종속 94.44% 인식율을 구하였다.