• Journal of Information Processing Systems
• /
• 제14권1호
• /
• pp.218-227
• /
• 2018

Vocal effort detection is important for both robust speech recognition and speaker recognition. In this paper, the spectral information entropy feature which contains more salient information regarding the vocal effort level is firstly proposed. Then, the model fusion method based on complementary model is presented to recognize vocal effort level. Experiments are conducted on isolated words test set, and the results show the spectral information entropy has the best performance among the three kinds of features. Meanwhile, the recognition accuracy of all vocal effort levels reaches 81.6%. Thus, potential of the proposed method is demonstrated.

• 대한원격탐사학회지
• /
• 제22권4호
• /
• pp.295-304
• /
• 2006

영상융합은 "특정 알고리즘의 사용을 통해 두 개 혹은 그 이상의 서로 다른 영상을 조합하여 새로운 영상을 만들어내는 것"을 뜻하며 원격탐사에서는 주로 낮은 공간해상도의 멀티스펙트럴 영상과 높은 공간해상도의 흑백영상을 융합하여 높은 공간해상도의 멀티스펙트럴 영상을 생성하는 것을 의미한다. 일반적으로 하이퍼스펙트럴 영상융합을 위해서는 기존의 멀티스펙트럴 영상융합 기법을 이용한 방법이나 분광혼합기법을 이용한 방법을 사용한다. 전자의 경우에는 분광정보가 손실될 가능성이 높으며, 후자의 경우는, endmember의 정보나 부가적인 데이터가 필요하고 결과 영상의 경우 공간적 정보가 상대적으로 부정확한 문제점을 보인다. 따라서 본 연구에서는 하이퍼스펙트럴 영상의 분광특성을 보존하기 위한 융합방법으로서 2단계 분광혼합기법을 사용한 영상융합 알고리즘을 제안하였으며 이를 실제 Hyperion, ALI 영상에 적용하여 평가하였다. 이를 통해 제안한 알고리즘에 의해서 융합된 결과가 PCA, GS 융합기법에 비해서 높은 공간, 분광 해상도를 유지할 수 있음을 보여주었다.

• Current Optics and Photonics
• /
• 제5권4호
• /
• pp.431-443
• /
• 2021

Sparse unmixing has been proven to be an effective method for hyperspectral unmixing. Hyperspectral images contain rich spectral and spatial information. The means to make full use of spectral information, spatial information, and enhanced sparsity constraints are the main research directions to improve the accuracy of sparse unmixing. However, many algorithms only focus on one or two of these factors, because it is difficult to construct an unmixing model that considers all three factors. To address this issue, a novel algorithm called multiview-based spectral weighted and low-rank row-sparsity unmixing is proposed. A multiview data set is generated through spectral partitioning, and then spectral weighting is imposed on it to exploit the abundant spectral information. The row-sparsity approach, which controls the sparsity by the l_2,0 norm, outperforms the single-sparsity approach in many scenarios. Many algorithms use convex relaxation methods to solve the l_2,0 norm to avoid the NP-hard problem, but this will reduce sparsity and unmixing accuracy. In this paper, a row-hard-threshold function is introduced to solve the l_2,0 norm directly, which guarantees the sparsity of the results. The high spatial correlation of hyperspectral images is associated with low column rank; therefore, the low-rank constraint is adopted to utilize spatial information. Experiments with simulated and real data prove that the proposed algorithm can obtain better unmixing results.

• Current Optics and Photonics
• /
• 제7권5호
• /
• pp.518-528
• /
• 2023

As an effective means of remotely detecting the spectral information of the object, the spectral calibration for the Savart polarization interference imaging spectrometer (SPIIS) is a basis and prerequisite of information quantification, and its experimental calibration scheme is firstly proposed in this paper. In order to evaluate the accuracy of the spectral information acquisition, the linear interpolation, cubic spline interpolation, and piecewise cubic interpolation algorithms are adopted, and the precision of the quadratic polynomial fitting is the highest, whose fitting error is better than 5.8642 nm in the wavelength range of [500 nm, 820 nm]. Besides, the inversed value of the spectral resolution for the monochromatic light is greater than the theoretical value, and the deviation between them becomes larger with the wavelength increasing, which is mainly caused by the structural design of the SPIIS, together with the rationality of the spectral restoration algorithm and the selection of the maximum optical path difference (OPD). This work demonstrates that the SPIIS has achieved high performance assuring the feasibility of its practical use in various fields.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 춘계 학술대회 발표논문집
• /
• pp.53-56
• /
• 2005

In this paper, we propose a transformation based robust adaptation technique that uses the maximum mutual information(MMI) estimation for the objective function and the linear spectral transformation(LST) for adaptation. LST is an adaptation method that deals with environmental noises in the linear spectral domain, so that a small number of parameters can be used for fast adaptation. The proposed technique is called MMI-LST, and evaluated on TIMIT and FFMTIMIT corpora to show that it is advantageous when only a small amount of adaptation speech is used.

• Journal of Multimedia Information System
• /
• 제5권1호
• /
• pp.63-66
• /
• 2018

In this work, the smoothing and the interpolation basis splines are analyzed. As well as the possibility of using the spectral properties of the basis splines for digital signal processing are shown. This takes into account the fact that basic splines represent finite, piecewise polynomial functions defined on compact media.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2003년도 하계종합학술대회 논문집 Ⅳ
• /
• pp.2415-2418
• /
• 2003

In this paper, we present a new filter to adjust formant information. Spectral envelope in speech analysis shows information about characteristics of speech and formant information determines speech timbre. So, if formant position is adjusted, we can verify adjusted speech timbre. A presented filter is to adjust this formant. This filter is composed of triangular filters. Using this filter we could locate the formant frequency at target position.

• Journal of Communications and Networks
• /
• 제11권1호
• /
• pp.1-10
• /
• 2009

In this paper, we propose a chip-level detection and a spectral-slice scheme for the tunable-transmitter/fixed-receiver (TTFR)-based asynchronous spectral phase-encoded optical codedivision multiple-access (CDMA) system combined with timeencoding. The chip-level detection can enhance the tolerance of multiple access interference (MAI) because the channel collision does not occur as long as there is at least one weighted position without MAI. Moreover, the spectral-slice scheme can reduce the interference probability because the MAI with the different frequency has no adverse effects on the channel collision rate. As a result, these techniques mitigate channel collisions. We analyze the channel collision rate theoretically, and show that the proposed system can achieve a lower channel collision rate in comparison to both conventional systems with and without the time-encoding method.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2004년도 추계학술발표회 논문집
• /
• pp.251-256
• /
• 2004

The image classification is one of the most important studies in the remote sensing. In general, the MLC(Maximum Likelihood Classification) classification that in consideration of distribution of training information is the most effective way but it produces a bad result when we apply it to actual hyperspectral image with the same classification technique. The purpose of this research is to reveal that which one is the most effective and suitable way of the classification algorithms iii the hyperspectral image classification. To confirm this matter, we apply the MLC classification algorithm which has distribution information and SAM(Spectral Angle Mapper), SFF(Spectral Feature Fitting) algorithm which use average information of the training class to both multispectral image and hyperspectral image. I conclude this result through quantitative and visual analysis using confusion matrix could confirm that SAM and SFF algorithm using of spectral pattern in vector domain is more effective way in the hyperspectral image classification than MLC which considered distribution.

• 정보과학회 논문지
• /
• 제43권6호
• /
• pp.686-691
• /
• 2016

본 논문에서는 다수의 특징, 특히 셋 이상의 특징을 가지는 데이터에 대한 분광 군집 방법인 적응형 분광 군집 방법을 소개하고, 적응형 분광 군집 방법의 성능을 시뮬레이션 데이터와 다중 언어 데이터를 이용하여 분석한다. 적응형 분광 군집 방법에서는 특징 간 서로 다른 정보들을 공유하여 데이터를 군집화함으로써 군집 성능을 높인다. 이때, 서로 다른 특징 간의 정보 공유를 효율적으로 하기 위해, 협업학습을 도입했다. 협업 학습에서는 각 특징이 서로 독립이 되도록 가중치를 학습하고, 학습된 가중치에 따라 정보를 전달한다. 이러한 과정을 통해 일반적인 특징 결합이나, 모든 특징 간 독립을 가정한 기존 협업학습 기반의 분광 군집에 비해 정보 공유의 효율성을 높인다. 실험에서는 시뮬레이션 데이터와 다중 언어문서 데이터를 이용하여 성능을 검증하였으며, 반복과정에서의 성능 변화와 정보 전달 결과 변화하는 모습을 제시함으로써 적응형 분광 군집 방법의 유의미한 성능 향상에 대해 분석하였다.