• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.211-214
• /
• 2003

일반적으로 음성 인식에서의 성능은 잡음의 영향으로 인하여 저하된다. 전화망을 통한 한국어 연속 숫자음 인식은 음성인식 분야에 있어서 어려운 영역에 속하는데, 이는 조음 현상으로 인한 인식률 저하되는 점과 전화망 채널의 영향으로 인하여 스펙트럼 포락이 왜곡되며 음성신호의 대역폭이 제한되기 때문이다. 본 논문에서는 잡음의 영향을 줄이기 위하여, 2WF(2-stage Wiener Filter) 와 SWP (SNR-dependent Waveform Processing) 그리고 CMN(Cepstrum Mean Normalization)을 사용하였다. 2WF는 음성 신호의 포만트 구조를 적게 왜곡시키면서 전체적인 가산잡음 뿐만 아니라 동적 가산잡음도 줄여준다. SWP는 음성파형에서 SNR값이 상대적으로 큰 부분을 강조하여 전체적인 SNR을 향상시킬 수 있다. 또한, CMN은 특징벡터로부터 채널잡음의 영향을 정규화하여 음성 인식 성능을 향상시킨다. 이러한 방법들을 전화망 한국어 연속 숫자음 DB를 이용하여 실험한 결과, 음성신호의 왜곡을 최소화하면서 잡음의 영향을 줄여 전화망에서의 숫자음 인식 성능을 향상시킬 수 있었다.

• Structural Monitoring and Maintenance
• /
• v.2 no.3
• /
• pp.237-252
• /
• 2015

This paper addresses the issue of reliability and performance in wireless sensor networks (WSN) based structural health monitoring (SHM), particularly with decentralized damage identification techniques. Two decentralized damage identification algorithms, namely, the autoregressive (AR) model based damage index and the Wiener filter method are developed for structural damage detection. The ambient and impact testing have been carried out on the steel beam structure in the laboratory. Seven wireless sensors are installed evenly along the steel beam and seven wired sensor are also installed on the beam to monitor the dynamic responses as comparison. The results showed that wireless measurements performed very much similar to wired measurements in detecting and localizing damages in the steel beam. Therefore, apart from the usual advantages of cost effectiveness, manageability, modularity etc., wireless sensors can be considered a possible substitute for wired sensors in SHM systems.

• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1606-1613
• /
• 2021

Recently various attempts to control hardware through integration of sensors and artificial intelligence have been made. This paper proposes a smart hazardous sound detection at home. Previous sound recognition methods have problems due to the processing of background sounds and the low recognition accuracy of high-frequency sounds. To get around these problems, a new MFCC(Mel-Frequency Cepstral Coefficient) algorithm using Wiener filter, modified filterbank is proposed. Experiments for comparing the performance of the proposed method and the original MFCC were conducted. For the classification of feature vectors extracted using the proposed MFCC, DNN(Deep Neural Network) was used. Experimental results showed the superiority of the modified MFCC in comparison to the conventional MFCC in terms of 1% higher training accuracy and 6.6% higher recognition rate.

• Journal of the Korea Computer Graphics Society
• /
• v.6 no.3
• /
• pp.9-15
• /
• 2000

We Propose a sensor fusion technique for motion capture system. In our system, two kinds of sensors are used for mutual assistance. Four magnetic sensors(markers) are attached on the upper arms and the back of the hands for assisting twelve optical sensors which are attached on the arms of a performer. The optical sensor information is not always complete because the optical markers can be hidden due to obstacles. In this case, magnetic sensor information is used to link discontinuous optical sensor information. We use a system identification techniques for modeling the relation between the sensors' signals. Dynamic systems are constructed from input-output data. We determine the best model from the set of candidate models using the canonical system identification techniques. Our approach is using a simple signal processing technique currently. In the future work, we will propose a new method using other signal processing techniques such as Wiener or Kalman filter.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.5
• /
• pp.35-43
• /
• 1999

In this paper, a new robust adaptive algorithm and a post-processing method are proposed to improve the performance of AEC without computational burden. Its step-size is normalized by the sum of the powers of the reference input signal and the desired signal. When the near-end speaker's speech and noise are applied into the microphone, the step-size becomes small and the misalignment of coefficients are reduced. To reduce the residual echoes, a new post-processing method, which is co-operated with the proposed noise-robust adaptive algorithm, is proposed in this paper. The method is based on the correlation of the desired signal and the estimation error signal. The residual echoes are attenuated as proportional to the correlation normalized with the power of desired signals. The normalized correlation plays a role as Wiener filter for residual echoes. In the double-talk situation, the estimation error signals, that are residual echoes, dominantly include the near-end speaker's speech and the normalized correlation closes to 1. Therefore, the near-end speaker's speech can be transmitted without being attenuated. When the desired signals consists of only the acoustic echoes, the residual echoes are mostly attenuated and canceled by the proposed post-processor. The computation of AEC using the proposed post-processor is comparable to NLMS algorithm.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.28 no.8C
• /
• pp.795-802
• /
• 2003

It is very important to construct statistical model in order to exactly estimate the signal variance from a noisy image. In order to estimate variance, information of neighboring region is used generally. The size of neighbor region is varied according to the regional characteristics of image. More accurate estimation of edge variance is due to smaller region of neighbor, on the other hands, larger region of neighbor is used to estimate the variance of flat region. By using estimated variance of original image, in general, Wiener filter is constructed, and it is applied to the noisy image. In this paper, we propose a new method for determining the range of neighbors to estimate the variance in wavelet domain. Firstly, a significance map is constructed using the parent-child relationship of wavelet domain. Based on the number of the significant wavelet coefficients, the range of neighbors is determined and then the variance of the original signal is estimated using ML(maximum likelihood method. Experimental results show that the proposed method yields better results than conventional methods for image denoising.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.38C no.2
• /
• pp.189-195
• /
• 2013

In this paper, a land and maritime unified tourism information guide system is proposed which employs robust speech recognition in ship noise environments. Most of conventional front-ends for speech recognition have used a Wiener filter to compensate for stationary noise such as car or babble noises. However, such the conventional front-ends have limitation in reducing non-stationary noise that are occurred inside the ship on voyage. To overcome such a limitation, the proposed system incorporates nonlinear multi-band spectral subtraction to provide highly accurate tourism route recognition. It is shown from the experiment that compared to a conventional system the proposed system achieves relative improvement of a tourism route recognition rate by 5.54% under a noise condition of 10 dB signal-to-noise ratio (SNR).

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.34 no.3
• /
• pp.309-316
• /
• 2010

In this study, a digital particle holographic system and its application to channel-flow measurements were investigated. A double-exposure hologram recording system that is capable of recording digital holograms in a short time interval was developed. A correlation coefficient method was used to determine the focal plane of particles. The Wiener filter was used to remove noises and improve image quality. Two-threshold and image segmentation methods were used for binary image transformation. The cross-correlation method was used for particle pairing. The developed system was employed to study channel flow fields, and the axial velocities of channel flow were measured. The measurement errors are acceptable, and this proves the feasibility of using the digital particle holographic system as a good tool for flow-field measurements.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.42 no.6
• /
• pp.19-26
• /
• 2005

Image interpolation in the wavelet domain usually takes advantage of the probabilistic models for the intrascale statistics and the interscale dependency. In this paper, we adopt the linear model for the absolute values of wavelet coefficients of interpolated image across scale to estimate the variances of extrapolated bands. The proposed algorithm uses randomly generated wavelet coefficients based on the estimated parameters for probabilistic model. Random number generation according to the estimated probabilistic model may induce the 'salt and pepper' noise in subbands. We reduce the noise power by Wiener filtering. We observe that the proposed method generates the histogram of the subband coefficients similar to the that of original image. Experimental results show that our method outperforms the previous wavelet-domain interpolation method as well as the conventional bicubic method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.11C
• /
• pp.911-916
• /
• 2010

This paper proposes a new algorithm to cancel the acoustic feedback and noise signals in digital hearing aids. The proposed algorithm combines the feedback canceller to remove acoustic feedback signals and the noise canceller to reduce background noises. The feedback canceller is implemented by normal adaptive FIR filter, and the noise canceller is implemented by using the Wiener solution in frequency domain. This noise canceller has the transfer function presented by the power spectral density of signals. To verify the performances of the proposed algorithm, the simulations were carried out for the system. As the results of simulations, it was proved that we can advance 10.85dB output SNR on the average for the forward path gain of 0dB, and 11.04dB output SNR on the average for the forward path gain of 6dB, in the case of using the proposed algorithm.