• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.10
• /
• pp.1867-1872
• /
• 2016

In the area of digital signal processing, it is necessary to improve the quality of the speech signal after removing the background noise which exists in a various real environments. The important thing to consider when removing the background noise acoustically is that to solve the problem, depending on the information of the human auditory mechanism is mainly the amplitude spectrum of the speech signal. This paper introduces the characteristics of a frequency-weighted spectrum shaping filter for the extraction of the amplitude spectrum of the speech signal with the primary purpose. Therefore, this paper proposes an algorithm using the methods of a Wiener filter and the frequency-weighted spectrum shaping filter according to the acoustic model, after extracted the amplitude spectral information in the noisy speech signal. The spectral distortion (SD) output of the proposed algorithm is experimentally improved more than 5.28 dB compared to a conventional method.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.4
• /
• pp.174-182
• /
• 1996

In continuous speech recognition system, it is possible to implement the system which can handle unlimited number of words by using limited number of phonetic units such as phonemes. Dividing continuous speech into the string of tems of phonemes prior to recognition process can lower the complexity of the system. But because of the coarticulations between neiboring phonemes, it is very difficult ot extract exactly their boundaries. In this paper, we propose the algorithm ot extract short terms which can represent each phonemes instead of extracting their boundaries. The short terms of lower spectral change and higher spectral chang eare detcted. Then phoneme changes are detected using distance measure with this lower spectral change terms, and hgher spectral change terms are regarded as transition terms or short phoneme terms. Finally lower spectral change terms and the mid-term of higher spectral change terms are regarded s the represent each phonemes. The cepstral coefficients and weighted cepstral distance are used for speech feature and measuring the distance because of less computational complexity, and the speech data used in this experimetn was recoreded at silent and ordinary in-dorr environment. Through the experimental results, the proposed algorithm showed higher performance with less computational complexity comparing with the conventional segmetnation algorithms and it can be applied usefully in phoneme-based continuous speech recognition.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.686-689
• /
• 2002

This paper proposes a weighted least-squares(WLS) method for designing variable one-dimensional (1-D) FIR digital filters with simultaneously variable magnitude and variable non-integer phase-delay responses. First, the coefficients of a variable FIR filter are represented as the two-dimensional (2-D) polynomials of a pair of spectral parameters: one is for tuning the magnitude response, and the other is for varying its non-integer phase-delay response. Then the optimal coefficients of the 2-D polynomials are found by minimizing the total weighted squared error of the variable frequency response. Finally, we show that the resulting variable FIR filter can be implemented in a parallel form, which is suitable for high-speed signal processing.

• Journal of information and communication convergence engineering
• /
• v.21 no.3
• /
• pp.208-215
• /
• 2023

Deep learning techniques provide powerful solutions to several pattern-recognition problems, including Raman spectral classification. However, these networks require large amounts of labeled data to perform well. Labeled data, which are typically obtained in a laboratory, can potentially be alleviated by data augmentation. This study investigated various data augmentation techniques and applied multiple deep learning methods to Raman spectral classification. Raman spectra yield fingerprint-like information about chemical compositions, but are prone to noise when the particles of the material are small. Five augmentation models were investigated to build robust deep learning classifiers: weighted sums of spectral signals, imitated chemical backgrounds, extended multiplicative signal augmentation, and generated Gaussian and Poisson-distributed noise. We compared the performance of nine state-of-the-art convolutional neural networks with all the augmentation techniques. The LeNet5 models with background noise augmentation yielded the highest accuracy when tested on real-world Raman spectral classification at 88.33% accuracy. A class activation map of the model was generated to provide a qualitative observation of the results.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.20 no.10
• /
• pp.3371-3380
• /
• 1996

Low resolution spectral modeling of water vapor is carried out by applying the weighted-sum-of-gray-gases model (WSGGM) to a narrow band. For a given narrow band, focus is placed on proper modeling of gray gas absorption coefficients vs. temeprature relation used for any solution methods for the Radiative Transfer Equation(RTE). Comparison between the modeled emissivity and the "true" emissivity obtained from a high temperatue statistical narrow band parameters is made ofr the total spectrum as well as for a few typical narrow bands. Application of the model to nonuniform gas layers is also made. Low resolution spectral intensities at the boundary are obtained for uniform, parabolic and boundary layer type temeprature profiles using the obtained for uniform, parabolic and boundary layer type temperature profiles using the obtained WSGGM's with 9 gray gases. The results are compared with the narrow band spectral intensities as obtained by a narrow band model-based code with the Curtis-Godson approximation. Good agreement is found between them. Local heat source strength and total wall heat flux are also compared for the cases of Kim et al, which again gives promising agreement.

• Journal of the Korean Mathematical Society
• /
• v.51 no.1
• /
• pp.203-224
• /
• 2014

We propose and analyze a spectral Jacobi-collocation approximation for fractional order integro-differential equations of Fredholm-Volterra type. The fractional derivative is described in the Caputo sense. We provide a rigorous error analysis for the collection method, which shows that the errors of the approximate solution decay exponentially in $L^{\infty}$ norm and weighted $L^2$-norm. The numerical examples are given to illustrate the theoretical results.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1998.08a
• /
• pp.250-253
• /
• 1998

In digital communicatioin networks, speech recognition systems conventionally reconstruct speech followed by extracting feature [parameters. In this paper, we consider a useful approach by incorporating speech coding parameters into the speech recognizer. Most speech coders employed in the networks represent line spectral pairs as spectral parameters. In order to improve the recognition performance of the LSP-based speech recognizer, we introduce two different ways: one is to devise weighed distance measures of LSPs and the other is to transform LSPs into a new feature set, named a pseudo-cepstrum. Experiments on speaker-independent connected-digit recognition showed that the weighted distance measures significantly improved the recognition accuracy than the unweighted one of LSPs. Especially we could obtain more improved performance by using PCEP. Compared to the conventional methods employing mel-frequency cepstral coefficients, the proposed methods achieved higher performance in recognition accuracies.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.450-453
• /
• 2000

In this paper, an automated segmentation algorithm is proposed for MR brain images using T1-weighted, T2-weighted, and PD images complementarily. The proposed segmentation algorithm is composed of 3 steps. In the first step, cerebrum images are extracted by putting a cerebrum mask upon the three input images. In the second step, outstanding clusters that represent inner tissues of the cerebrum are chosen among 3-dimensional (3D) clusters. 3D clusters are determined by intersecting densely distributed parts of 2D histogram in the 3D space formed with three optimal scale images. Optimal scale image best describes the shape of densely distributed parts of pixels in 2D histogram. In the final step, cerebrum images are segmented using FCM algorithm with it’s initial centroid value as the outstanding cluster’s centroid value. The proposed segmentation algorithm complements the defect of FCM algorithm, being influenced upon initial centroid, by calculating cluster’s centroid accurately And also can get better segmentation results from the proposed segmentation algorithm with multi spectral analysis than the results of single spectral analysis.

• Korean Journal of Remote Sensing
• /
• v.25 no.6
• /
• pp.507-515
• /
• 2009

Land surface temperature (LST) is a key environmental variable in a wide range of applications, such as weather, climate, hydrology, and ecology. However, LST is one of the most difficult surface variables to observe regularly due to the strong spatio-temporal variations. So, we have developed the LST retrieval algorithm from COMS (Communication, Ocean and Meteorological Satellite) data through the radiative transfer simulations under various atmospheric profiles (TIGR data), satellite zenith angle (SZA), spectral emissivity, and surface lapse rate conditions using MODTRAN 4. However, the LST retrieval algorithm has a tendency to overestimate and underestimate the LST for surface inversion and superadiabatic conditions, respectively. To minimize the overestimation and underestimation of LST, we also developed day/night LST algorithms separately based on the surface lapse rate (local time) and recalculated the final LST by using the weighted sum of day/night LST. The analysis results showed that the quality of weighted LST of day/night algorithms is greatly improved compared to that of LST estimated by original algorithm regardless of the surface lapse rate, spectral emissivity difference (${\Delta}{\varepsilon}$) SZA, and atmospheric conditions. In general, the improvements are greatest when the surface lapse rate and ${\Delta}{\varepsilon}$ are negatively large (strong inversion conditions and less vegetated surface).

• Nuclear Engineering and Technology
• /
• v.55 no.10
• /
• pp.3907-3912
• /
• 2023

Radiation portal monitors (RPMs) installed at airports and harbors to prevent illicit trafficking of radioactive materials generally use large plastic scintillators. However, their energy resolution is poor and radionuclide identification is nearly unfeasible. In this study, to improve isotope identification, a RPM system based on a multi-array plastic scintillator and convolutional neural network (CNN) was evaluated by measuring the spectra of radioactive sources. A multi-array plastic scintillator comprising an assembly of 14 hexagonal scintillators was fabricated within an area of 50 × 100 cm². The energy spectra of ¹³⁷Cs, ⁶⁰Co, ²²⁶Ra, and ⁴K (KCl) were measured at speeds of 10-30 km/h, respectively, and an energy-weighted algorithm was applied. For the CNN, 700 and 300 spectral images were used as training and testing images, respectively. Compared to the conventional plastic scintillator, the multi-arrayed detector showed a high collection probability of the optical photons generated inside. A Compton maximum peak was observed for four moving radiation sources, and the CNN-based classification results showed that at least 70% was discriminated. Under the speed condition, the spectral fluctuations were higher than those under dwelling condition. However, the machine learning results demonstrated that a considerably high level of nuclide discrimination was possible under source movement conditions.