• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.05a
• /
• pp.341-344
• /
• 2009

본 논문에서는 신경회로망(Neural network)에 시간구조를 도입한 시간지연 신경회로망(Time-delay Neural Network: TDNN)을 사용하여 잡음을 포함한 음성신호로부터 잡음을 제거함으로써 음성을 강조하는 것을 목적으로 한다. 본 논문에서는 먼저 각 프레임의 FFT 진폭성분들을 유성음 구간과 무성음 구간으로 검출한 후, 무성음 구간에 대해서는 각 프레임에서 이동평균을 취하여 음성을 강조한다. 유성음 구간에 대해서는 각 프레임의 FFT 진폭성분들을 저역, 중역 및 고역으로 각각 분리한 후에 각 대역의 FFT 진폭성분들을 저역용 TDNN, 중역용 TDNN, 그리고 고역용 TDNN의 입력으로 하여 각 TDNN에 학습시킴으로써 최종 FFT 진폭성분들을 구한다. 본 실험에서는 Aurora2 데이터베이스를 사용하여 FFT의 진폭성분을 복원하는 잡음제거의 알고리즘을 사용하여 여러 잡음에 대해서 본 알고리즘의 유효성을 실험적으로 확인한다.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.2
• /
• pp.240-245
• /
• 2019

This paper is a study result on long distance transmission of underwater acoustic sensor data over cable. The data transceiver is designed using the LVDS (Low Voltage Differential Signaling) transmission scheme, and the jitter characteristics are analyzed by measuring the long distance transmission signal through the cable. In order to reduce the jitter, a pre-emphasis technique is applied to compensate the transmitting signal to be attenuated by long distance transmission, and the transmission characteristics were verified according to the distance.

• Journal of the Korean Society of Radiology
• /
• v.8 no.6
• /
• pp.301-307
• /
• 2014

In this study, an image acquired by the DSA(Digital Subtraction Angiography) system that is configured to configure the algorithm for high pass filtering algorithm experiments to improve the quality of angiography methods proposed. high pass filter is a high-frequency components pass through the filter, blocking low-frequency components. Part of the boundary line and contour of the organ corresponds to the high-frequency component is a high-frequency component of a medical image. Therefore, the high pass filter is also used for detection of the boundary line, but is also used for the high frequency enhancement. It was able to be analyzed by the proposed algorithm, to improve the quality of the angiography. Found out that the expression of the target site stand out clearly. The quality of the DSA system proposed in the wrong diagnosis software can be used to reduce, it is possible to develop and will further improve the accuracy of the treatment.

• Proceedings of the Korea Institute of Convergence Signal Processing
• /
• 2000.12a
• /
• pp.109-112
• /
• 2000

고역의 주파수 성분이 감쇠되어 선명도가 저하된 이미지나 선형 보간법에 의해 확대된 이미지의 계단모양 왜곡을 감소시킴으로써 경계선의 선명도가 저하된 이미지들을 위해 형태학적 처리(morphological processing)에 의한 이미지 윤곽선의 선명도를 향상시키는 방법을 제안하였다. 본 논문에서는 블러링(blurring)된 이미지를 화소의 명암에 따라 다수개의 평판 이미지(slice image)로 나누고 각 평판 이미지에 대해 반복적인 최대/최소값 필터(min/max filter)의 적용으로 얻어진 윤곽선의 중심을 기준으로 하여 팽창(dilation)과 침식(erosion)을 수행함으로 이미지의 윤곽선에서의 명암 변화에 대한 경사도를 크게 만들고 이로써 이미지 윤곽선의 선명도를 향상시키는 방법을 사용하였으며 모의 시험결과를 통하여 고역 주파수 강조에 의한 방법에 비하여 인위적인 잡음(artifact)없이 효과적으로 선명도를 향상시킬 수 있음을 보였다.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.3
• /
• pp.61-67
• /
• 2001

In this paper, a method that apply LP algorithm to image for speech recognition is suggested, using both speech and image information for recogniton of korean numeral speech. The input speech signal is pre-emphasized with parameter value 0.95, analyzed for B th LP coefficients using Hamming window, autocorrelation and Levinson-Durbin algorithm. Also, a gray image signal is analyzed for 2-dimensional LP coefficients using autocorrelation and Levinson-Durbin algorithm like speech. These parameters are used for input parameters of neural network using back-propagation algorithm. The recognition experiment was carried out at each noise level, three numeral speechs, '3','5', and '9' were enhanced. Thus, in case of recognizing speech with 2-dimensional LP parameters, it results in a high recognition rate, a low parameter size, and a simple algorithm with no additional feature extraction algorithm.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.7
• /
• pp.1571-1576
• /
• 2013

This paper proposes an improvement algorithm of signal-to-noise ratios (SNRs) for speech signals under noisy environments. The proposed algorithm first estimates the SNRs in a low SNR, mid SNR and high SNR areas, in order to improve the SNRs in the speech signal from background noise, such as white noise and car noise. Thereafter, this algorithm subtracts the noise signal from the noisy speech signal at each bands using a spectrum sharpening method. In the experiment, good signal-to-noise ratios (SNR) are obtained for white noise and car noise compared with a conventional spectral subtraction method. From the experiment results, the maximal improvement in the output SNR results was approximately 4.2 dB and 3.7 dB better for white noise and car noise compared with the results of the spectral subtraction method, in the background noisy environment, respectively.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.1
• /
• pp.74-81
• /
• 2003

In this study, we'd implemented a real time embedded speech recognition system that requires minimum memory size for speech recognition engine and DB. The word to be recognized consist of 40 commands used in a PCS phone and 10 digits. The speech data spoken by 15 male and 15 female speakers was recorded and analyzed by short time analysis method, which window size is 256. The LPC parameters of each frame were computed through Levinson-Burbin algorithm and they were transformed to Cepstrum parameters. Before the analysis, speech data should be processed by pre-emphasis that will remove the DC component in speech and emphasize high frequency band. Baum-Welch reestimation algorithm was used for the training of HMM. In test phone, we could get a recognition rate using likelihood method. We implemented an embedded system by porting the speech recognition engine on ARM core evaluation board. The overall recognition rate of this system was 95%, while the rate on 40 commands was 96% and that 10 digits was 94%.