• Phonetics and Speech Sciences
• /
• v.4 no.4
• /
• pp.87-92
• /
• 2012

Speech enhancement aims to improve speech quality by removing background noise from noisy speech. Independent vector analysis is a type of frequency-domain independent component analysis method that is known to be free from the frequency bin permutation problem in the process of blind source separation from multi-channel inputs. This paper proposed a new method of microphone array based speech enhancement that combines independent vector analysis and beamforming techniques. Independent vector analysis is used to separate speech and noise components from multi-channel noisy speech, and delay-sum beamforming is used to determine the enhanced speech among the separated signals. To verify the effectiveness of the proposed method, experiments for computer simulated multi-channel noisy speech with various signal-to-noise ratios were carried out, and both PESQ and output signal-to-noise ratio were obtained as objective speech quality measures. Experimental results have shown that the proposed method is superior to the conventional microphone array based noise removal approach like GSC beamforming in the speech enhancement.

• Current Optics and Photonics
• /
• v.4 no.1
• /
• pp.69-80
• /
• 2020

A Rayleigh Lidar used for wind detection works by transmitting laser pulses to the atmosphere and receiving backscattering signals from molecules. Because of the weak backscattering signals, a lidar usually uses a high sensitivity photomultiplier as detector and photon counting technology for signal collection. The capturing of returned extremely weak backscattering signals requires the lidar to work on dark background with a long time accumulation to get high signal-to-noise ratio (SNR). Because of the strong solar background during the day, the SNR of lidar during daytime is much lower than that during nighttime, the altitude and accuracy of detection are also restricted greatly. Therefore this article describes an ultra-narrow bandwidth filter (UNBF) that has been developed on 354.7 nm wavelength of laser. The UNBF is used for suppressing the strong solar background that degrades the performance of Rayleigh wind lidar during daytime. The optical structure of UNBF consists of an interference filter (IF), a low resolution Fabry-Perot interferometer (FPI) and a high resolution FPI. The parameters of each optical component of the UNBF are presented in this article. The transmission curve of the aligned UNBF is measured with a tunable laser. Contrasting the result of with-UNBF and with-IF shows that the solar background received by a Licel transient recorder decreases by 50~100 times and that the SNR with-UNBF was improved by 3 times in the altitude range (35 km to 40 km) compared to with-IF at 10:26 to 10:38 on August 29, 2018. By the SNR comparison at four different times of one day, the ratio-values are larger than 1 over the altitude range (25~50 km) in general, the results illustrate that the SNR with-UNBF is better than that with-IF for Rayleigh Lidar during daytime and they demonstrate the effective improvements of solar background restriction of UNBF.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.6
• /
• pp.1793-1801
• /
• 2016

Speech enhancement is a challenging problem due to the diversity of noise sources and their effects in different applications. The goal of speech enhancement is to improve the quality and intelligibility of speech by reducing noise. Many research works in speech enhancement have been accomplished in English and other European Languages. There has been limited or no such works or efforts in the past in the context of Tamil speech enhancement in the literature. The aim of the proposed method is to reduce the background noise present in the Tamil speech signal by using wavelets. New modified thresholding function is introduced. The proposed method is evaluated on several speakers and under various noise conditions including White Gaussian noise, Babble noise and Car noise. The Signal to Noise Ratio (SNR), Mean Square Error (MSE) and Mean Opinion Score (MOS) results show that the proposed thresholding function improves the speech enhancement compared to the conventional hard and soft thresholding methods.

• 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.

• MALSORI
• /
• no.49
• /
• pp.145-158
• /
• 2004

This paper is aiming at implementation of real-time speaker verification system using DSP board. Dialog/4, which is based on microprocessor and DSP processor, is selected to easily control telephone signals and to process audio/voice signals. Speaker verification system performs signal processing and feature extraction after receiving voice and its ID. Then through computing the likelihood ratio of claimed speaker model to the background model, it makes real-time decision on acceptance or rejection. For the verification experiments, total 15 speaker models and 6 background models are adopted. The experimental results show that verification accuracy rates are 99.5% for using telephone speech-based speaker models.

• Journal of Photoscience
• /
• v.4 no.1
• /
• pp.11-16
• /
• 1997

We measured, using femtosecond pump-probe experiment, the time evolution of transient absorption in aqueous CdS colloids. The signal rises within the time resolution (= 0.5 ps) of the experiment and decays with two exponential time constants, 4.8 ps and 132 ps. The ultrafast rise of the transient absorption is considered to be for shallowly trapped conduction band electrons after photoexcitation. The amplitude ratio of the two decaying components varies with the pump intensity and the decay times increase in the presence of hole scavengers. Even though a biexponential function fits the decay well, we object hat two independent first order processes (geminate and nongeminate recombinations) are responsible for the decay. A function with an integrated rate equation for second order nongeminate recombination plus a long background fits the decay well. The long background is considered to be for deeply trapped charges at the CdS particle.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.4
• /
• pp.817-822
• /
• 2011

This paper first proposes the speech recognition algorithm by detection of the speech and noise sections at each frame using a neural network training by back-propagation algorithm, then proposes the spectral subtraction method which removes the noises at each frame according to detection of the speech and noise sections. In this experiment, the performance of the proposed recognition system was evaluated based on the recognition rate using various speeches that are degraded by white noise and car noise. Moreover, experimental results of the noise reduction by the spectral subtraction method demonstrate using the speech and noise sections detecting by the speech recognition algorithm at each frame. Based on measuring signal-to-noise ratio, experiments confirm that the proposed algorithm is effective for the speech by corrupted the noise using signal-to-noise ratio.

• Journal of Institute of Control, Robotics and Systems
• /
• v.14 no.5
• /
• pp.415-419
• /
• 2008

Detecting and correcting defects on LCD glasses early in the manufacturing process becomes important for panel makers to reduce the manufacturing costs and to improve productivity. Many attempts have been made and were successfully applied to detect and identify simple defects such as scratches, dents, and foreign objects on glasses. However, it is still difficult to robustly detect low-contrast defect region, called Mura or blemish area on glasses. Typically, these defect areas are roughly defined as relatively large, several millimeters of diameter, and relatively dark and/or bright region of low Signal-to-Noise Ratio (SNR) against background of low-frequency signal. The aim of this article is to present a robust algorithm to segment these blemish defects. Early 90's, a highly robust estimator, known as the Model-Fitting (MF) estimator was developed by X. Zhuang et. al. and have been successfully used in many computer vision application. Compared to the conventional Least-Square (LS) estimator the MF estimator can successfully estimate model parameters from a dataset of contaminated Gaussian mixture. Such a noise model is defined as a regular white Gaussian noise model with probability $1-\varepsilon$ plus an outlier process with probability $varepsilon$. In the sense of robust estimation, the blemish defect in images can be considered as being a group of outliers in the process of estimating image background model parameters. The algorithm developed in this paper uses a modified MF estimator to robustly estimate the background model and as a by-product to segment the blemish defects, the outliers.

• Journal of Yeungnam Medical Science
• /
• v.37 no.2
• /
• pp.90-97
• /
• 2020

Background: To minimize damage to the ovarian reserve, it is necessary to evaluate the follicular density in the ovarian tissue surrounding endometriosis on preoperative imaging. The purpose of the present study was to evaluate the usefulness of subtraction pelvic magnetic resonance imaging (MRI) to detect ovarian reserve. Methods: A subtracted T1-weighted image (^subT1WI) was obtained by subtracting unenhanced T1WI from contrast-enhanced T1WI (^ceT1WI) with similar parameters in 22 patients with ovarian endometriosis. The signal-to-noise ratio (SNR) in ovarian endometriosis, which was classified into the high signal intensity and iso-to-low signal intensity groups on the T2-weighted image, was compared to that in normal ovarian tissue. To evaluate the effect of contrast enhancement, a standardization map was obtained by dividing ^subT1WI by ^ceT1WI. Results: On visual assessment of 22 patients with ovarian endometriosis, 16 patients showed a high signal intensity, and 6 patients showed an iso-to-low signal intensity on T1WI. Although SNR in endometriosis with a high signal intensity was higher than that with an iso-to-low signal intensity, there was no difference in SNR after the subtraction (13.72±77.55 vs. 63.03±43.90, p=0.126). The area of the affected ovary was smaller than that of the normal ovary (121.10±22.48 vs. 380.51±75.87 ㎟, p=0.002), but the mean number of pixels in the viable remaining tissue of the affected ovary was similar to that of the normal ovary (0.53±0.09 vs. 0.47±0.09, p=0.682). Conclusion: The subtraction technique used with pelvic MRI could reveal the extent of endometrial invasion of the normal ovarian tissue and viable remnant ovarian tissue.

• Journal of Radiation Protection and Research
• /
• v.38 no.1
• /
• pp.29-36
• /
• 2013

The aim of this study was to determine the correlation between exposure index (EI) and dose factors related to radiation dose optimization in digital radiography (DR) system. Two phantoms with built-in regional test object for quantitative assessment of images were used to produce image signals that acquired in chest radiography background. EI and entrane surface dose (ESD) increased proportionally with rise of radiation dose (kVp, mAs) in both DR and CR systems. Especially, DR detector was effective to form good contrast and hence, reached easily to improvement of image quality with minimal dose changes. It made operators possible to expect the accuracy of EI values deeply related to absorbed dose of the detector. The evaluation of images was obtained specially employed calculation of noise to signal ratio (NSR) and contrast to noise ratio (CNR). These measurements were performed for how exposure factors affect image quality. NSR was inversely proportional to kVp and mAs and low NSR represented high signal detection efficiency. Consequently, EI values was the measure of the amount of exposure received by the image receptor and it was proportional to exposure factors. Therefore the EI in a recommended range from manufacturer can offer optimal image quality. Also, continuous monitoring of EI values in the digital radiography can reduce the unnecessary patient dose and help the quality control of the system.