• The Journal of the Acoustical Society of Korea
• /
• v.22 no.2E
• /
• pp.62-68
• /
• 2003

This paper addresses a novel noise-compensation scheme to solve the mismatch problem between training and testing condition for the automatic speech recognition (ASR) system, specifically in car environment. The conventional spectral subtraction schemes rely on the signal-to-noise ratio (SNR) such that attenuation is imposed on that part of the spectrum that appears to have low SNR, and accentuation is made on that part of high SNR. However, these schemes are based on the postulation that the power spectrum of noise is in general at the lower level in magnitude than that of speech. Therefore, while such postulation is adequate for high SNR environment, it is grossly inadequate for low SNR scenarios such as that of car environment. This paper proposes an efficient spectral subtraction scheme focused specifically to low SNR noisy environment by extracting harmonics distinctively in speech spectrum. Representative experiments confirm the superior performance of the proposed method over conventional methods. The experiments are conducted using car noise-corrupted utterances of Aurora2 corpus.

• Proceedings of the KSPS conference
• /
• 2006.05a
• /
• pp.131-134
• /
• 2006

The narrowband speech over the telephone network is lacking in the information from low-band (0-300 Hz) and high-band (3400-8000 Hz) that are found in wideband speech (0-8000 Hz). As a result, narrowband speech is characterized by the reduced intelligibility and muffled quality, and degraded speaker identification. Spectral folding is the easiest way to reconstruct the missing high-band; however, the reconstructed speech still brings the sense of band-limited characteristic because of the absence of low-band and mid-band frequency components. To compensate for the lack of the extended speech, we propose to combine the spectral folding method and GMM transformation method, which is a statistical method to reconstruct wideband speech. The reconstructed wideband speech showed that the absent frequency components was filled up with relatively low spectral mismatch. According to the subjective speech quality evaluations, the proposed method was preferred to other methods.

• The Bulletin of The Korean Astronomical Society
• /
• v.41 no.1
• /
• pp.76.2-76.2
• /
• 2016

We present near-infrared (0.8 - 1.8 microns) spectra of 63 bright (J_mag < 10) stars observed with Low Resolution Spectrometer (LRS) onboard the rocket-borne Cosmic Infrared Background Experiment (CIBER). Two Micron All Sky Survey (2MASS) photometry information is used to find cross-matched stars after reduction and extraction of the spectra. We identify the spectral types of observed stars by comparing with spectral templates from the Infrared Telescope Facility (IRTF) library. All the observed spectra are consistent with late F to M stellar spectral types, and we identify various infrared absorption lines. As our observations are performed above the Earth's atmosphere, our spectra are free from telluric contamination. Including HST/NICMOS and Cassini/VIMS, the spectral coverage has rarely been achieved in space, and the methods developed here can inform statistical studies with future low-resolution spectral measurements such as GAIA photometric and radial velocity spectrometer.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.283-285
• /
• 2003

This paper describes a data fusion method for high spatial resolution satellite imagery. The pixels located around an object edge have spectral mixing because of the geometric primitive of pixel. The larger a size of pixel is, the wider an area of spectral mixing is. The intensity of pixels adjacent edges were modified by the spectral characteristics of the pixels located inside of objects. The methods developed in this study were tested using IKONOS Multispectral and Pan data of a part of Jeju-shi in Korea. The test application shows that the spectral information of the pixels adjacent edges were improved well.

• Journal of Information Processing Systems
• /
• v.15 no.4
• /
• pp.748-764
• /
• 2019

In order to deal with the filtering delay problem of least mean square adaptive filter noise reduction algorithm and music noise problem of spectral subtraction algorithm during the speech signal processing, we combine these two algorithms and propose one novel noise reduction method, showing a strong performance on par or even better than state of the art methods. We first use the least mean square algorithm to reduce the average intensity of noise, and then add spectral subtraction algorithm to reduce remaining noise again. Experiments prove that using the spectral subtraction again after the least mean square adaptive filter algorithm overcomes shortcomings which come from the former two algorithms. Also the novel method increases the signal-to-noise ratio of original speech data and improves the final noise reduction performance.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.35 no.10
• /
• pp.438-444
• /
• 1986

The signal can be modeled as a linear combination of its past values and present and past values of a hypothetical input to system whose output is given signal. Using this model spectral estimation problem can be reduced to estimate the ARMA parameters. This paper presents recursive modified instrumental variable algorithm which can estimate AR and MA parameters. For more accurate estimation, overdetermined modified IV algorithm is also derived. Computer simulations are presented to illustrate the above methods.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.52 no.2
• /
• pp.162-170
• /
• 2015

Commute time embedding involves computing the spectral decomposition of the graph Laplacian. It requires the computational burden proportional to $o(n^3)$, not suitable for large scale dataset. Many methods have been proposed to accelerate the computational time, which usually employ the Nystr${\ddot{o}}$m methods to approximate the spectral decomposition of the reduced graph Laplacian. They suffer from the lost of information by dint of sampling process. This paper proposes to reduce the errors by approximating the spectral decomposition of the graph Laplacian using that of the affinity matrix. However, this can not be applied as the data size increases, because it also requires spectral decomposition. Another method called approximate commute time embedding is implemented, which does not require spectral decomposition. The performance of the proposed algorithms is analyzed by computing the commute time on the patch graph.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2004.03a
• /
• pp.493-498
• /
• 2004

The objective of the present study is to compare various conventional and recently evolved satellite image-processing techniques and to ascertain the best possible technique that can identify and position of aquaculture farms accurately in and around the Younggwang coastal area. Several conventional techniques performed to extract such information fiom the Landsat-TM imagery do not seem to yield better information about the aquaculture farms, and lead to misclassification. The large errors between the actual and extracted aquaculture farm information are due to existence of spectral confusion and inadequate spatial resolution of the sensor. This leads to possible occurrence of mixture pixels or 'mixels' of the source of errors in the classification techniques. Understanding the confusing and mixture pixel problems requires the development of efficient methods that can enable more reliable extraction of aquaculture farm information. Thus, the more recently evolved methods such as the step-by-step partial spectral end-member extraction and linear spectral unmixing methods are introduced. The farmer one assumes that an end-member, which is often referred to as 'spectrally pure signature' of a target feature, does not appear to be a spectrally pure form, but always mix with the other features at certain proportions. The assumption of the linear spectral unmxing is that the measured reflectance of a pixel is the linear sum of the reflectance of the mixture components that make up that pixel. The classification accuracy of the step-by-step partial end-member extraction improved significantly compared to that obtained from the traditional supervised classifiers. However, this method did not distinguish the aquaculture ponds and non-aquaculture ponds within the region of the aquaculture farming areas. In contrast, the linear spectral unmixing model produced a set of fraction images for the aquaculture, water and soil. Of these, the aquaculture fraction yields good estimates about the proportion of the aquaculture farm in each pixel. The acquired proportion was compared with the values of NDVI and both are positively correlated (R$^2$ =0.91), indicating the reliability of the sub-pixel classification.ixel classification.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.17 no.3
• /
• pp.311-320
• /
• 1999

This study conducts to analyze comparative accuracy when both Image Transformation Methods and Supervised Classifications on multi-spectral TM using a case of Lower Tumen River Area. In terms of overall classification accuracy, maximum likelihood method turns out higher than other one, but in a case of vegetation only, MNF and TC image transformation methods produce a better quality of the result. Especially, seven dimensional images including MNF, TC, and NDVI create better image than three dimensional one. Among these transformation methods, maximum likelihood method results out the best one. Multi-spectral image could be useful as an important basic material for site selection of industrial allocation as well as Tumen River Area Economic Development Plan.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.1
• /
• pp.61-66
• /
• 1999

In this paper, we proposed various speaker adaptation methods and studied the performance of these methods. Methods which were studied in this paper are MAPE(Maximum A Posteriori Probability Estimation), Linear Spectral Estimating, Multi-Layer Perceptron and ARTMAP. In order to evaluate the performance of these methods, we used Korean isolated digits as the experimental data, the hybrid speaker adaptation method, which unified MAPE, linear spectral estimating and output probability of SCHMM, showed the better recognition result than those which performed other methods. And the method using ARTMAP showed the similar result to above hybrid method.