• The Journal of the Acoustical Society of Korea
• /
• 제22권2E호
• /
• 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.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2006년도 춘계 학술대회 발표논문집
• /
• 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.

• 천문학회보
• /
• 제41권1호
• /
• 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.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2003년도 Proceedings of ACRS 2003 ISRS
• /
• 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
• /
• 제15권4호
• /
• 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.

• 대한전기학회논문지
• /
• 제35권10호
• /
• 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.

• 전자공학회논문지
• /
• 제52권2호
• /
• pp.162-170
• /
• 2015

컴뮤트 타임 임베딩을 구현하려면 그래프 라플라시안 행렬의 고유값과 고유벡터를 구하여야 하는데, $o(n^3)$의 계산량이 요구되어 대용량 데이터에는 적용하기 어려운 문제가 있다. 이를 줄이기 위하여 표본화 과정을 통하여 크기가 줄어든 그래프 라플라시안 행렬에서 구한 다음, 원래의 고유값과 고유벡터를 근사화시키는 Nystr${\ddot{o}}$m 기법을 주로 채택한다. 이 과정에서 많은 오차가 발생하는데, 이를 개선하기 위하여 본 논문에서는 그래프 라플라시안 대신에 가중치 행렬을 표본화하고 이로부터 구한 고유값과 고유벡터를 그래프 라플라시안의 고유값과 고유벡터로 변환하는 기법을 이용하여 대용량 데이터로 구성된 스펙트럴 그래프를 근사적으로 컴뮤트 타임 임베딩하는 기법을 제안한다. 하지만, 이 방식도 스펙트럼 분해를 계산하여야 하므로 데이터의 크기가 증가하면 적용하기 어려운 문제가 발생한다. 이의 대안으로, 스펙트럼 분해를 계산하지 않고도 데이터 집합의 크기에 영향을 받지 않으면서 컴뮤트 타임을 근사적으로 계산하는 방식을 구현하고 이들의 특성을 실험적으로 분석한다.

• 한국GIS학회:학술대회논문집
• /
• 한국GIS학회 2004년도 GIS/RS 공동 춘계학술대회 논문집
• /
• 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.

• 한국측량학회지
• /
• 제17권3호
• /
• pp.311-320
• /
• 1999

본 연구에서는 두만강 하류지역 다분광 TM영상의 변환기법과 그에 대한 감독분류방법을 비교 분석하였다. 총체적 분류 정확도는 최대우도법이 높으며 식생은 MNF와 TC 변환 영상에서 비교적 좋은 분류 결과를 얻을 수 있다. MNF, TC, NDVI 등 영상들로 구성된 7차원 영상은 3차원 영상보다 좋은 결과를 나타내며 그 중에서도 최대우도법의 분류 결과가 제일 좋았다. 다분광 영상은 두만강 지역 경제 개발 계획과 산업 입지 선정에 중요한 기초자료로 활용될 수 있다.

• 한국음향학회지
• /
• 제18권1호
• /
• pp.61-66
• /
• 1999

본 논문은 화자 적응 방법 제안과 그 방법들의 성능을 검토한 것이다. 본 논문에서 제안 검토한 방법들은 최대사후확률추정(MAPE)방법, 음성 선형 특성을 이용한 방법, 다층 퍼셉트론(MLP)을 이용한 방법과 ARTMAP을 이용한 방법들이다. 각 방법들의 성능 평가를 위하여 한국어 숫자음으로 실험한 결과, 최대사후확률추정 방법과 반연속 HMM의 출력 확률적응, 음성 선형 특성 등 3방법을 결합한 방법이 가장 우수한 결과를 보였으며, 이와 비슷한 실험 결과를 ARTMAP을 이용한 화자 적응 방법에서 보였다.