• International journal of advanced smart convergence
• /
• v.9 no.2
• /
• pp.20-27
• /
• 2020

Sound event detection in real-world environments suffers from the interference of non-stationary and time-varying noise. This paper presents an adaptive noise reduction method for sound event detection based on non-negative matrix factorization (NMF). In this paper, we proposed a deep learning model that integrates Convolution Neural Network (CNN) with Non-Negative Matrix Factorization (NMF). To improve the separation quality of the NMF, it includes noise update technique that learns and adapts the characteristics of the current noise in real time. The noise update technique analyzes the sparsity and activity of the noise bias at the present time and decides the update training based on the noise candidate group obtained every frame in the previous noise reduction stage. Noise bias ranks selected as candidates for update training are updated in real time with discrimination NMF training. This NMF was applied to CNN and Hidden Markov Model(HMM) to achieve improvement for performance of sound event detection. Since CNN has a more obvious performance improvement effect, it can be widely used in sound source based CNN algorithm.

• Journal of computational fluids engineering
• /
• v.22 no.1
• /
• pp.103-109
• /
• 2017

The aerodynamic noise reduction of railway traction motor is required to satisfy new enhanced Korean noise regulations for a train. This paper is the study result on a noise reduction of a railway traction motor using Lattice Boltzmann Method(LBM). To verify the reliability of numerical analysis, the noise performance of the base model evaluated using LBM, and calculated result was compared with the experimental data. In addition, main noise sources were selected to design parameters through analyzing the flow field of the base model. Based on the noise sources analysis result, a design improvement model of traction motor for this study was derived to reduce the noise. The performance of a design improvement model was evaluated by applying a validated numerical scheme. As a result, it was confirmed that the noise was reduced due to the suppression of the internal turbulent flow components.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.12 no.7
• /
• pp.1180-1186
• /
• 2008

The LNB phase noise of user terminal for high data rate satellite transmission was analyzed in this paper. The phase noise severely affects the service performance in low data rate transmission as well as multi-mode signal for high data rate. As the satellite link frequency is increased, the effects of phase noise for multi-mode signal is increased. The phase noise of LNB, which is operated in high frequency band, is about equal to the transmission system phase noise and have an major effects on service performance degradation. The available transmission mode was analyzed in presence of phase noise of LNB and analysis method for LNB phase noise spectrum distribution was proposed in multi-mode signal.

• Journal of Digital Contents Society
• /
• v.1 no.1
• /
• pp.39-52
• /
• 2000

In this paper, we derive the BER performance of an asynchronous DS/CDMA system and analyze the improvement of BER performance through turbo coding and RAKE receiver in multipath Rayleigh fading and impulsive noise environments. As a result, impulsive noise affects the performance of the system more than multipath fading in lower $E_b/N_o$ than a certain threshold. However, in higher $E_b/N_o$, multipath fading are more dominant than impulsive noise. It is found that in lower $E_b/N_o$, turbo code improves the performance of the system against impulsive noise, and in higher $E_b/N_o$, RAKE receiver improves the performance of the system against multipath fading. Therefore, great improvement can be obtained by employing turbo code and RAKE receiver in multipath Rayleigh fading and impulsive noise environments.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.48 no.1
• /
• pp.101-107
• /
• 2011

The background noises and distortions by channel are major factors that disturb the practical use of speech recognition. Usually, noise reduce the performance of speech recognition system DSR(Distributed Speech Recognition) based speech recognition also bas difficulty of improving performance for this reason. Therefore, to improve DSR-based speech recognition under noisy environment, this paper proposes a method which detects accurate speech region to extract accurate features. The proposed method distinguish speech and noise by using entropy and detection of spectral energy of speech. The speech detection by the spectral energy of speech shows good performance under relatively high SNR(SNR 15dB). But when the noise environment varies, the threshold between speech and noise also varies, and speech detection performance reduces under low SNR(SNR 0dB) environment. The proposed method uses the spectral entropy and harmonics of speech for better speech detection. Also, the performance of AFE is increased by precise speech detections. According to the result of experiment, the proposed method shows better recognition performance under noise environment.

• Journal of Korea Society of Industrial Information Systems
• /
• v.11 no.3
• /
• pp.15-19
• /
• 2006

In shallow water active sonar environment, reverberation which is a non-white noise is one of the main source of performance degradation of target detection. In this case, the received signal is whitened before applying matched filter known as an optimum filter in the presence of white noise. However implementation of this method is very difficult because of the non-stationary characteristic of reverberation. Traditionally reverberation is assumed local stationary. In this paper, we estimate a range of stationary of reverberation signal, and then propose a pre-whitening method which improve the performance of pre-whitening block normalized matched filter in presence of non-white reverberation noise. Proposed whitener shows better whitening performance than traditional whitener because it use later as well as before reverberation of target signal. To evaluate performance of the proposed whitener, an actual measurement data sampled at the East-Sea is used for computer simulation. The target detector with new whitener is shown better performance than detector with traditional whitener.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.1
• /
• pp.43-51
• /
• 2005

In this paper, we propose an algorithm that improves a tone quality of a noisy audio signal in order to enhance a Performance of perceptual filter using noise energy control. Most of the algorithms which were proposed by the other researchers usually applied a filter using the noise energy acquired from a silent range. In this case. the improvement rate of tone quality decreases if the noise energy is changed by the magnitude or environment variation in a signal frame. But the Proposed method Provides the means to find a food estimated noise through energy control of the estimated noise which is obtained from a silent range. Also we can get the enhancement of tone qualify in low frequency band unlike other methods. To show the performance of the Proposed algorithm, various input signals which had a different signal-to-noise ratio (SNR) such as 5dB, l0dB, 15dB and 20dB were used to test the proposed algorithm. With the proposed algorithm, we could confirm the enhancement of tone quality in terms of segmental SNR (SSNR). noise-to-mask ration (NMR) and mean opinion score (MOS) test.

• Journal of Korean Society of Environmental Engineers
• /
• v.39 no.12
• /
• pp.679-684
• /
• 2017

Recently, the speed of high-speed railway has been rapidly increase with the development of high-speed train design and operating technology. This causes a lot of complaints related the environmental noise in residential areas near the high-speed railway. In order to operate the high-speed railway in accordance with the design speed, noise reduction technology should be developed to meet the noise characteristics of high-speed railway. And it is important to develop the prediction technology by grasping the noise radiation characteristics. In order to meet these requirements, in recent years, infra-research for 400 km/h high speed railway has been conducted. Reliable noise prediction and noise reduction techniques have been developed through this study. This paper is concerned with wind pressure safety and noise performance evaluation of the newly developed 400 km/h noise reduction device. The wind pressure safety and The noise performance of the developed device was confirmed by this paper.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.4
• /
• pp.526-532
• /
• 2022

With the development of IoT technology, image processing is being utilized in various fields such as image analysis, image recognition, medical industry, and factory automation. Noise is generated in image data from causes such as defect in transmission line. Image noise must be removed because it damages the performance of the image processing application program. Salt and Pepper noise is a representative type of image noise, and various studies have been conducted to remove Salt and Pepper noise. Widely known methods include A-TMF, AFMF, and SDWF. However, as the noise density increases, the performance deteriorates. Thus, this paper proposes an algorithm that performs filtering using a fuzzy logic weight mask only in case of noise after noise determination. In order to prove the noise removal performance of the proposed algorithm, an experiment was performed on images with 10% to 90% noise added and the PSNR was compared.

• International Journal of Computer Science & Network Security
• /
• v.22 no.11
• /
• pp.308-318
• /
• 2022

Noise is a serious issue. While sending images via electronic communication, Impulse noise, which is created by unsteady voltage, is one of the most common noises in digital communication. During the acquisition process, pictures were collected. It is possible to obtain accurate diagnosis images by removing these noises without affecting the edges and tiny features. The New Average High Noise Density Median Filter. (HNDMF) was proposed in this paper, and it operates in two steps for each pixel. Filter can decide whether the test pixels is degraded by SPN. In the first stage, a detector identifies corrupted pixels, in the second stage, an algorithm replaced by noise free processed pixel, the New average suggested Filter produced for this window. The paper examines the performance of Gaussian Filter (GF), Adaptive Median Filter (AMF), and PHDNF. In this paper the comparison of known image denoising is discussed and a new decision based weighted median filter used to remove impulse noise. Using Mean Square Error (MSE), Peak Signal to Noise Ratio (PSNR), and Structure Similarity Index Method (SSIM) metrics, the paper examines the performance of Gaussian Filter (GF), Adaptive Median Filter (AMF), and PHDNF. A detailed simulation process is performed to ensure the betterment of the presented model on the Mini-MIAS dataset. The obtained experimental values stated that the HNDMF model has reached to a better performance with the maximum picture quality. images affected by various amounts of pretend salt and paper noise, as well as speckle noise, are calculated and provided as experimental results. According to quality metrics, the HNDMF Method produces a superior result than the existing filter method. Accurately detect and replace salt and pepper noise pixel values with mean and median value in images. The proposed method is to improve the median filter with a significant change.