• The Journal of the Acoustical Society of Korea
• /
• v.41 no.1
• /
• pp.38-44
• /
• 2022

Speech enhancement is performed to improve intelligibility and quality of the noise-corrupted speech. In this paper, speech enhancement performance was compared using different loss functions in time and frequency domains. This study proposes a combination of loss functions to utilize advantage of each domain by considering both the details of spectrum and the speech waveform. In our study, Scale Invariant-Source to Noise Ratio (SI-SNR) is used for the time domain loss function, and Mean Squared Error (MSE) is used for the frequency domain, which is calculated over the complex-valued spectrum and magnitude spectrum. The phase loss is obtained using the sin function. Speech enhancement result is evaluated using Source-to-Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short-Time Objective Intelligibility (STOI). In order to confirm the result of speech enhancement, resulting spectrograms are also compared. The experimental results over the TIMIT database show the highest performance when using combination of SI-SNR and magnitude loss functions.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.6
• /
• pp.544-551
• /
• 2023

Speech enhancement used to improve the perceptual quality and intelligibility of noise speech has been studied as a method using a complex-valued spectrum that can improve both magnitude and phase in a method using a magnitude spectrum. In this paper, a study was conducted on how to apply attention mechanism to complex-valued spectrum-based speech enhancement systems to further improve the intelligibility and quality of noise speech. The attention is performed based on additive attention and allows the attention weight to be calculated in consideration of the complex-valued spectrum. In addition, the global average pooling was used to consider the importance of the feature map. Complex-valued spectrum-based speech enhancement was performed based on the Deep Complex U-Net (DCUNET) model, and additive attention was conducted based on the proposed method in the Attention U-Net model. The results of the experiments on noise speech in a living room environment showed that the proposed method is improved performance over the baseline model according to evaluation metrics such as Source to Distortion Ratio (SDR), Perceptual Evaluation of Speech Quality (PESQ), and Short Time Object Intelligence (STOI), and consistently improved performance across various background noise environments and low Signal-to-Noise Ratio (SNR) conditions. Through this, the proposed speech enhancement system demonstrated its effectiveness in improving the intelligibility and quality of noisy speech.

• Korean Journal of Air-Conditioning and Refrigeration Engineering
• /
• v.24 no.1
• /
• pp.23-28
• /
• 2012

In the present work, numerical analyses of air flow in HVAC duct have been carried out for enhancement of cooling/heating performance. For the analyses, three-dimensional Reynolds-averaged Navier-Stokes equations have been solved with the shear stress transport turbulence model. The numerical results were validated in comparison with the experimental data. Based on the numerical results, the HVAC duct was designed to reduce the pressure loss. The modified duct geometry shows largely reduced pressure drop in comparison with the reference geometry. And, through modified duct shape, the performance of air conditioning has been enhanced.

• Journal of Positioning, Navigation, and Timing
• /
• v.1 no.1
• /
• pp.51-57
• /
• 2012

In this paper, design of an error model is presented in which the bias characteristic of the MEMS IMU is taken into consideration for performance enhancement of the MEMS IMU-based GPS/INS integrated navigation system. The drift bias of the MEMS IMU is modeled as a 1st-order Gauss-Markov (GM) process, and the autocorrelation function is obtained from the collected IMU data, and the correlation time is estimated from this. Prior to obtaining the autocorrelation function, the noise of IMU data is eliminated based on wavelet. As a result of simulation, it is represented that the parameters of error model can be estimated correctly only when a proper denoising is performed according to dynamic behavior of drift bias, and that the integrated navigation system based on error model, in which the drift bias is considered, provides more correct navigation performance compared to the integrated navigation system based on error model in which the drift bias is not considered.

• Bulletin of the Korean Chemical Society
• /
• v.32 no.6
• /
• pp.2058-2062
• /
• 2011

The effect of the addition of ionic liquids with four different cations (imidazolium, pyrrolidinium, piperidinium and pyridinium) on the performance of dye-sensitized $TiO_2$ solar cells based on electrolytes containing a t-butylpyridine (TBP) in 3-methoxypropionitrile (MPN) was studied. A total of 18 ionic liquids with mono-, di- and tri-alkyl derivatives were used in the present study, and among them a pyridinium cation with a mono-alkyl group showed better cell efficiency than the others. The best photoelectric conversion efficiency, 7.213%, was obtained using 1-hexylpyridinium iodide with an open-circuit photovoltage ($V_{oc}$) = 0.731 V, a short-circuit photocurrent density ($J_{sc}$) = 16.175 $mA/cm^2$, and a fill factor (ff) = 0.610 under AM1.5 and 100 $mW/cm^2$ illumination.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.4
• /
• pp.897-904
• /
• 2011

In this paper, a novel circuit topology of a low-noise amplifier tunable at 1.8GHz band for PCS and 2.4GHz band for WLAN using a CMOS active inductor is proposed. This circuit topology to reduce higher noise figure of the low noise amplifier with the CMOS active load is analyzed. Furthermore, the noise canceling technique is adopted to reduce more the noise figure. The noise figure of the proposed circuit topology is analyzed and simulated in $0.18{\mu}m$ CMOS process technology. Thus, the simulation results exhibit that the noise performance enhancement of the tunable low noise amplifier is about 3.4dB, which is mainly due to the proposed new circuit topology.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.8B
• /
• pp.727-734
• /
• 2008

Recently, Network technology evolve out of expansion a scale of Network and development various Service. also Hacking skill. We have applied to various Security Systems to make a counterattack on this hacking skill. and A Firewall among these security systems is very effective a defense against in the Outbound Network attack. so we need certainly a Firewall to protect a network. But this Conventional Firewall has an directly effect on reduction to the Performance and Security of Inbound Network. and have no effect on a Inner Network Attacking. In this paper, I propose to a "Functional Firewall" as a Secure Objects for the enhancement Performance and Security of Inbound Network.

• International Journal of Control, Automation, and Systems
• /
• v.3 no.spc2
• /
• pp.322-333
• /
• 2005

This paper proposes a combination of the Thyristor Controlled Series Capacitor (TCSC) and Static Var Compensator (SVC) installation for enhancing the damping performance of a power system. The developed scheme employs a damping controller which coordinates measurement signals with control signals to control the TCSC and SVC. The coordinated control method is based on the application of projective controls. Controller performance over a range of operating conditions is investigated through simulation studies on a single-machine infinite-bus power system. The linear analysis and nonlinear simulation results show that the proposed controller can significantly improve the damping performance of the power system and hence, increase its power transfer capabilities. In this paper, a current injection model of TCSC is developed and incorporated in the transmission system model. By using equivalent injected currents at terminal buses to simulate a TCSC no modification of the bus admittance matrix is required at each iteration.

• The Journal of the Acoustical Society of Korea
• /
• v.30 no.6
• /
• pp.330-336
• /
• 2011

In this paper, we propose a new method to improve the performance of supervector linear kernel SVM (Support Vector Machine) for speaker identification. This method is based on splitting one training datum into several pieces of utterances. We use four different databases for evaluating performance and use PCA (Principal Component Analysis), GKPCA (Greedy Kernel PCA) and KMDA (Kernel Multimodal Discriminant Analysis) for feature enhancement. As a result, the proposed method shows improved performance for speaker identification using supervector linear kernel SVM.

• The KSFM Journal of Fluid Machinery
• /
• v.19 no.5
• /
• pp.61-67
• /
• 2016

Turbine blade cooling is one of the major technologies to enhance the performance of gas turbine and combined cycle power plants. In this study, two cases of coolant pre-cooling schemes were applied in combined cycle power plant: decrease of coolant mass flow needed to cool turbine blade and increase of turbine inlet temperature (TIT). Both schemes are benefited by the decrease of coolant temperature through coolant pre-cooling. Under the same degree of pre-cooling, increasing TIT exhibits larger plant power boost and higher plant efficiency than reducing coolant flow. As a result, the former produces the same gas turbine power with a much smaller degree of pre-cooling than the latter. Another advantage of increasing TIT is a higher plant efficiency. Even with an assumption of partial achievement of the theoretically predicted TIT, the method of increasing TIT can provide considerably larger power output.