• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.11 no.3
• /
• pp.175-179
• /
• 2011

In this paper, we propose the MA(Model Adaption) HMM that to use speech enhancement and feature compensation. Normally voice reference data is not consider for real noise data. This method is not to use estimated noise but we use real life environment noise data. And we applied this contaminated data for recognition reference model that suitable for noise environment. MAHMM is combined with surround noise when generating reference patten. We improved voice recognition rate at mobile environment to use MAHMM.

• Phonetics and Speech Sciences
• /
• v.10 no.1
• /
• pp.33-38
• /
• 2018

Although deep neural network-based acoustic models have greatly improved the performance of automatic speech recognition (ASR), reverberation still degrades the performance of distant speech recognition in indoor environments. In this paper, we adopt the DenseNet, which has shown great performance results in image classification tasks, to improve the performance of reverberant speech recognition. The DenseNet enables the deep convolutional neural network (CNN) to be effectively trained by concatenating feature maps in each convolutional layer. In addition, we extend the concept of multi-resolution CNN to multi-resolution DenseNet for robust speech recognition in reverberant environments. We evaluate the performance of reverberant speech recognition on the single-channel ASR task in reverberant voice enhancement and recognition benchmark (REVERB) challenge 2014. According to the experimental results, the DenseNet-based acoustic models show better performance than do the conventional CNN-based ones, and the multi-resolution DenseNet provides additional performance improvement.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.2
• /
• pp.114-125
• /
• 1998

In this study, for the first time, we propose the ADI(Adaptive De-Interlacing) algorithm, which improves visually and subjectively, horizontal and vertical edges on the image processed by the ELA (Edge Based Line Average) method. The proposed ADI algorithm enlargesthe window size to 5*3 in order to utilize the feature of the continuity of edges, and the adaptive interpolator is employed to decide adaptiely horizontal, diagonal, and vertical edges. Based on the results of the compter simulation, it is confimed that the new ADI algorithm improve the PSNR by 0.5dB in the Lena image with 512*512 size and by 0.4dB in the sequence image of a salesman, respectively. For the horizontal and vertial edges on the still and salesman sequence images, the proposed ADI algorithm has better visulal improvement than the conventional ELA algorithm.

• Journal of computational fluids engineering
• /
• v.20 no.3
• /
• pp.70-78
• /
• 2015

Turbulent flow and heat transfer characteristics of textile machine are numerically investigated. To examine the influence of flow structures on the drying performance of fabrics, the nozzle shape of high temperature chamber is changed. For several nozzles, flow and heat transfer characteristics are discussed. The results show that the drying performance is improved by controlling the angle and arrangement of nozzles corresponding to different drying conditions. This feature is strongly related to the enhancement of turbulent fluctuations and secondary flows.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.222-223
• /
• 2016

보행자 인식을 위한 컴퓨터 비전 알고리즘은 야간 상황과 같이 저조도 환경에서는 인식 성능이 떨어지고 있다. 이로 인하여 최근 저조도 환경에서 촬영된 영상으로 야간 상황에서 객체 인식 성능을 높이는 기법들이 연구되고 있다. 야간 환경은 주간 환경과는 다르게 광량이 적기 때문에 인간의 시각으로도 객체 인식에 어려움이 있고 일반적인 카메라로 촬영된 영상으로 객체 인식이 어렵다. 최근에는 NIR 카메라를 이용하여 촬영된 영상으로 야간 보행자 인식 알고리즘이 개발되고 있으나, 인식률과 객체 인식 가능 거리 및 범위가 한정적이다. 또한 기존의 야간 보행자 검출 기법들은 방대한 연산량이 필요하기 때문에 실시간 객체 인식이 불가능하다. 본 논문에서는 NIR 카메라로부터 촬영된 영상으로 preprocessing 후 ACF(Aggregated Channel Feature)를 이용하여 최근 연구되고 있는 카메라 움직임이 있는 야간 환경에서 보행자 인식 알고리즘을 PC 및 TK1 Board 환경에서 구현하고 객체 인식률을 높인다.

• Journal of Korean Institute of Industrial Engineers
• /
• v.41 no.4
• /
• pp.408-413
• /
• 2015

The quality prediction of the semiconductor industry has been widely recognized as important and critical for quality improvement and productivity enhancement. The main objective of this paper is to predict the final quality of semiconductor chips based on fail bit count information obtained from probe tests. Our proposed method consists of solving the data imbalance problem, non-parametric variable selection, and adjusting the parameters of the model. We demonstrate the usefulness and applicability of the proposed procedure using a real data from a semiconductor manufacturing.

• Journal of Korea Multimedia Society
• /
• v.15 no.5
• /
• pp.569-576
• /
• 2012

This paper presents an x-ray medical image panorama system which can overcome the smallness of the images that exist on a source computer during remote medical processing. In the system, after the standard medical image format DICOM is converted to the PC standard image format, a MSR algorithm is used to enhance X-ray images of low quality. Then SURF and Multi-band blending are applied to generate a panoramic image. Also, this paper evaluates the proposed SURF based system through the average gray value error and image quality criterion with X-ray image data by comparing with a SIFT based system. The results show that the proposed system is superior to SIFT based system in image quality.

• The Transactions of the Korean Institute of Electrical Engineers C
• /
• v.50 no.10
• /
• pp.532-535
• /
• 2001

The sputtering condition of Cr thin film was established in order to get Cr gate electrode having a vertical wall structure for Mo-tip FEA. In case of Mo-tip FEA which had a vertically-etched Cr gate electrode, the field enhancement factor, was relatively increased and so the field emission performance in terms of turn-on voltage, emission current and trans-conductance could be improved when compared with the devices having a tapered gate wall.

• MALSORI
• /
• no.66
• /
• pp.73-86
• /
• 2008

Beamforming is one of the spatial filtering techniques which extract only desired signals from noisy environments using microphone arrays. Fixed beamforming is a simple concept and easy to implement. However, it does not show good performance in real noisy conditions. As an adaptive beamforming, Frost algorithm can be a good candidate. It uses the concept of the linearly constrained minimum variance (LCMV) algorithm. The difference between the Frost and the LCMV algorithm is the error correction scheme which is very effective feature in the aspect of performance. In this paper, as quadrature mirror filtering (QMF)-based filterbank is utilized as the pre-processing of the Frost beamformning, the filter length and the learning rate of each band is optimized to improve the performance. The performance is measured by the signal-to-noise ratio (SNR) and the Bark's scale spectral distortion (BSD).

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.59 no.6
• /
• pp.1143-1149
• /
• 2010

In this study, we propose a novel method to detect and enhance the feature of ST-segment which offers the crucial information for the diagnosis of myocardial infarction and ischemia. With this aim, PQRST features of Electrocardiogram initially are detected and subsequently ST-segment are estimated. And Dynamic Time Warping(DTW) transformation is applied recursively to minimize the difference in time between ST-segments and calculate the minimum cumulative distance that decides the degree of similarity among ST-segments. As of the results, the inherent characteristic of ST-segment can be emphasized in terms of time parameter and thus the diagnostic features of a ST-segment can be revealed further.