• The Journal of the Acoustical Society of Korea
• /
• v.20 no.7
• /
• pp.69-75
• /
• 2001

Intra-speaker variation, noise environments, and mismatch between training and test conditions are the major reasons for the speaker verification system unable to use it practically. In this study, we propose robust end-point detection algorithm, noise cancelling with the microphone property compensation technique, and inter-speaker discriminate technique by weighting cepstrum for robust speaker verification system. Simulation results show that the average speaker verification rate is improved in the rate of 17.65% with proposed end-point detection algorithm using LPC residue and is improved in the rate of 36.93% with proposed noise cancelling and microphone property compensation algorithm. The proposed weighting function for discriminating inter-speaker variations also improves the average speaker verification rate in the rate of 6.515%.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.8 no.3
• /
• pp.179-192
• /
• 2008

A multiphase compensation method with mismatch linearization technique, is presented and demonstrated in a $\Sigma-\Delta$ fractional-N frequency synthesizer. An on-chip delay-locked loop (DLL) and a proposed delay line structure are constructed to provide multiphase compensation on $\Sigma-\Delta$ quantizetion noise. In the delay line structure, dynamic element matching (DEM) techniques are employed for mismatch linearization. The proposed $\Sigma-\Delta$ fractional-N frequency synthesizer is fabricated in a $0.18-{\mu}m$ CMOS technology with 2.14-GHz output frequency and 4-Hz resolution. The die size is 0.92 mm$\times$1.15 mm, and it consumes 27.2 mW. In-band phase noise of -82 dBc/Hz at 10 kHz offset and out-of-band phase noise of -103 dBc/Hz at 1 MHz offset are measured with a loop bandwidth of 200 kHz. The settling time is shorter than $25{\mu}s$.

• MALSORI
• /
• no.52
• /
• pp.145-160
• /
• 2004

In this paper, a new noise compensation method based on the eigenvoice framework in feature space is proposed to reduce the mismatch between training and testing environments. The difference between clean and noisy environments is represented by the linear combination of K eigenvectors that represent the variation among environments. In the proposed method, the performance improvement of speech recognition systems is largely affected by how to construct the noisy models and the bias vector set. In this paper, two methods, the one based on MAP adaptation method and the other using stereo DB, are proposed to construct the noisy models. In experiments using Aurora 2 DB, we obtained 44.86% relative improvement with eigen-environment method in comparison with baseline system. Especially, in clean condition training mode, our proposed method yielded 66.74% relative improvement, which is better performance than several methods previously proposed in Aurora project.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.5
• /
• pp.112-121
• /
• 1997

In this paper, we study a model parameter compensation method for noise-robust speech recognition. We study model parameter compensation on a sentence by sentence and no other informations are used. Parallel model combination(PMC), well known as a model parameter compensation algorithm, is implemented and used for a reference of performance comparision. We also propose a modified PMC method which tunes model parameter with an association factor that controls average variability of gaussian mixtures and variability of single gaussian mixture per state for more robust modeling. We obtain a re-estimation solution of environmental variables based on the expectation-maximization(EM) algorithm in the cepstral domain. To evaluate the performance of the model compensation methods, we perform experiments on speaker-independent isolated word recognition. Noise sources used are white gaussian and driving car noise. To get corrupted speech we added noise to clean speech at various signal-to-noise ratio(SNR). We use noise mean and variance modeled by 3 frame noise data. Experimental result of the VTS approach is superior to other methods. The scheme of the zero order VTS approach is similar to the modified PMC method in adapting mean vector only. But, the recognition rate of the Zero order VTS approach is higher than PMC and modified PMC method based on log-normal approximation.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.4
• /
• pp.287-293
• /
• 2004

This paper proposes an efficient motion compensation algorithm for video sequences with brightness variations. In the proposed algorithm, the brightness variation parameters are estimated and local motions are compensated. To detect the frame with large brightness variations, we employ the frame classification based on the cross entropy between histograms of two successive frames, which can reduce the computational redundancy. Simulation results show that the proposed method yields a higher peak signal to noise ratio (PSNR) than that of the conventional methods, with a low computational load, when the video scene contains large brightness changes.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.1
• /
• pp.51-55
• /
• 2019

This paper proposes a speech enhancement method utilizing the feature compensation gain for robust speech recognition performances in noisy environments. In this paper we propose a speech enhancement method utilizing the feature compensation gain which is obtained from the PCGMM (Parallel Combined Gaussian Mixture Model)-based feature compensation method employing variational model composition. The experimental results show that the proposed method significantly outperforms the conventional front-end algorithms and our previous research over various background noise types and SNR (Signal to Noise Ratio) conditions in mismatched ASR (Automatic Speech Recognition) system condition. The computation complexity is significantly reduced by employing the noise model selection technique with maintaining the speech recognition performance at a similar level.

• ETRI Journal
• /
• v.29 no.3
• /
• pp.371-380
• /
• 2007

This paper proposes a new automatic compensation network (ACN) for a system-on-chip (SoC) transceiver. We built a 5 GHz low noise amplifier (LNA) with an on-chip ACN using 0.18 ${\mu}m$ SiGe technology. This network is extremely useful for today's radio frequency (RF) integrated circuit devices in a complete RF transceiver environment. The network comprises an RF design-for-testability (DFT) circuit, capacitor mirror banks, and a digital signal processor. The RF DFT circuit consists of a test amplifier and RF peak detectors. The RF DFT circuit helps the network to provide DC output voltages, which makes the compensation network automatic. The proposed technique utilizes output DC voltage measurements and these measured values are translated into the LNA specifications such as input impedance, gain, and noise figure using the developed mathematical equations. The ACN automatically adjusts the performance of the 5 GHz LNA with the processor in the SoC transceiver when the LNA goes out of the normal range of operation. The ACN compensates abnormal operation due to unusual thermal variation or unusual process variation. The ACN is simple, inexpensive and suitable for a complete RF transceiver environment.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.7 no.1
• /
• pp.11-19
• /
• 2007

This paper presents two novel compensation circuits for leakage current and power supply noise (PSN) in phase locked loop (PLL) using a nanometer CMOS technology. The leakage compensation circuit reduces the leakage current of the charge pump circuit which becomes more serious problem due to the thin gate oxide and small threshold voltage in nanometer CMOS technology and the PSN compensation circuit decreases the effect of power supply variation on the output frequency of VCO. The PLL design is based on a 32nm predictive CMOS technology and uses a 0.9V power supply voltage. The simulation results show that the proposed PLL achieves a 88% jitter reduction at 440MHz output frequency compared to the PLL without leakage compensator and its output frequency drift is little to 20% power supply voltage variations. The PLL has an output frequency range of $40M{\sim}725MHz$ with a multiplication range of 11023, and the RMS and peak-to-peak jitter are 5ps and 42.7ps, respectively.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.3
• /
• pp.221-229
• /
• 2013

In this paper, the image formation by the motion compensation technique for Synthetic Aperture Radar system(SAR) were realized through the computer simulation. The motion compensation technique performed image data with the range compression, the compensation procedure, the azimuth compensation and the noise elimination procedure. The range compression procedure transform the SAR raw data into the frequency domain and correlate with the range reference function and then inversely transform into the time domain. The compensation procedure contain the aircraft fluctuations compensation and the radar image degrading effect elimination procedure which was caused by image formation algorithm itself. The aircraft fluctuations compensation procedure perform the first stage which correct the phase angle and the second stage which calculate the Doppler frequency and determine the coordinate of the received signal. The radar image degrading effect elimination procedure also perform range migration compensation and the image defocussing effect compensation. The azimuth compression procedure transform the compensation data to the frequency domain and correlate with the azimuth reference function. The azimuth correlated data are inversely transformed to the time domain which is called SAR image data. When the above procedure were completed, the image data contains the received signals mixed with noise. The threshold technique was applied to elimination the noise from the mixed image data.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.26 no.3
• /
• pp.323-330
• /
• 2016

This paper describes real-time unbalance moment compensation method for line of sight(LOS) stabilization control systems. The factors of system inertia, frictions and unbalance moment affect the control accuracy of drive systems that are equipped to on the move(OTM) platforms requiring LOS stabilization function. In case of the unbalance moment among those factors is continuously changed as variation of relative angle between gravity vector and drive torque vector. Then, consideration of the effect in real-time is very complicate. Therefore, its effect should be designed to be minimized, however, designing it almost zero is impossible in real condition. In other words, it is hard to achieve target performance overcoming stability issue of highly unbalanced systems. To solve these problems, this paper proposes calculation method of unbalance moment by using measured sensor data for LOS stabilization control and its use for control compensation. Also, kinematical converting process and control structure for compensation are explained. The effectiveness of the proposed method as variation of unbalance moment is verified under simulation circumstance modeled by assuming LOS control system with 2-axis gimbal structure.