• 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.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.14 no.5
• /
• pp.811-816
• /
• 2019

This paper first proposes a technique to separate clean speech signals and mixed noise signals by using an independent vector analysis algorithm of frequency band for 4 channel speech source signals with a noise. An improved output speech signal from the proposed independent vector analysis algorithm is obtained by using the cross-correlation between the signal outputs from the frequency domain delay-sum beamforming and the output signals separated from the proposed independent vector analysis algorithm. In the experiments, the proposed algorithm improves the maximum SNRs of 10.90dB and the segmental SNRs of 10.02dB compared with the frequency domain delay-sum beamforming algorithm for the input mixed noise speeches with 0dB and -5dB SNRs including white noise, respectively. Therefore, it can be seen from this experiment and consideration that the speech quality of this proposed algorithm is improved compared to the frequency domain delay-sum beamforming algorithm.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.496-498
• /
• 2003

Signal is composed of the independent components that can describe itself. These components can distinguish itself from any other signals and be extracted by analysis itself. This algorithm is called Independent Component Analysis (ICA) and image signal is considered as linear combination of independent components and features that is the weighted vector of independent component. This algorithm is already used in order to extract the good feature for image classification and very effective In this paper, we'll explain the method of stereo matching using independent component analysis and show the experimental result.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.1E
• /
• pp.30-34
• /
• 2008

An improvement to the existing blind signal separation (BSS) method has been made in this paper. The proposed method models the inherent signal dependency observed in acoustic object to separate the real-world convolutive sound mixtures. The frequency domain approach requires solving the well known permutation problem, and the problem had been successfully solved by a vector representation of the sources whose multidimensional joint densities have a certain amount of dependency expressed by non-spherical distributions. Especially for speech signals, we observe strong dependencies across neighboring frequency bins and the decrease of those dependencies as the bins become far apart. The non-spherical joint density model proposed in this paper reflects this property of real-world speech signals. Experimental results show the improved performances over the spherical joint density representations.

• Journal of Power Electronics
• /
• v.13 no.1
• /
• pp.77-85
• /
• 2013

This paper proposes a new dead time compensation method of independent six-phase permanent magnet synchronous motors (IS-PMSM). The current of the independent phase machines contains odd-numbered harmonics because of the dead time and the nonlinear characteristics of the switching devices. By using the d-q-n three-dimensional vector analysis, these harmonics can be extracted at the n-axis current. Thus, the current distortion can be compensated by controlling the n-axis current of the IS-PMSM to zero. The proposed method is simple and can be easily implemented without additional hardware setup. The validity of the proposed compensation method is verified with simulations and several experiments.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.485-487
• /
• 2003

Independent Component Analysis (ICA) is used to generate ICA filter for computing feature vector for image window. Filters that have high discrimination power are selected to classify image from these ICA filters. Proposed classification algorithm is based on probability distribution of feature vector.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.195-200
• /
• 2004

In this paper we propose effective speech recognizer through two recognition experiments. In general, SVM is classification method which classify two class set by finding voluntary nonlinear boundary in vector space and possesses high classification performance under few training data number. In this paper we compare recognition performance of HMM and SVM at training data number and investigate recognition performance of each feature parameter while changing feature space of MFCC using Independent Component Analysis(ICA) and Principal Component Analysis(PCA). As a result of experiment, recognition performance of SVM is better than 1:.um under few training data number, and feature parameter by ICA showed the highest recognition performance because of superior linear classification.

• Proceedings of the Korean Information Science Society Conference
• /
• 1999.10b
• /
• pp.470-472
• /
• 1999

Sparse coding은 최소한의 active한 (non-orthogonal) basis vector를 이용하여 데이터를 표시하는 하나의 방법이다. Sparse coding에서 basis coefficient들이 statistically independent 하다는 constraint를 주기에 sparse coding은 independent component analysis(ICA)와 밀접한 관계를 가지고 있다. 본 논문에서는 sparse representation을 위하여 super-Gaussian prior를 이용한 ICA, 즉 sparse ICA 방법을 제시한다. Sparse ICA 방법을 이용하여 natural scenes의 basis vector를 찾고 이와 sparse coding과의 관계를 고찰한다. 여러 가지 super-Gaussian prior들을 고려하지 않고 이들이 ICA에 미치는 영향에 대해 살펴본다.

• International Journal of Contents
• /
• v.14 no.4
• /
• pp.24-29
• /
• 2018

EEG-based brain-computer interfaces has focused on explicitly expressed intentions to assist physically impaired patients. For EEG-based-computer interfaces to function effectively, it should be able to understand users' implicit information. Since it is hard to gather EEG signals of human brains, we do not have enough training data which are essential for proper classification performance of implicit intention. In this paper, we improve the subject independent classification of implicit intention through the generation of additional training data. In the first stage, we perform the PCA (principal component analysis) of training data in a bid to remove redundant components in the components within the input data. After the dimension reduction by PCA, we train ICA (independent component analysis) network whose outputs are statistically independent. We can get additional training data by adding Gaussian noises to ICA outputs and projecting them to input data domain. Through simulations with EEG data provided by CNSL, KAIST, we improve the classification performance from 65.05% to 66.69% with Gamma components. The proposed sample generation method can be applied to any machine learning problem with fewer samples.

• Journal of Biomedical Engineering Research
• /
• v.31 no.6
• /
• pp.456-463
• /
• 2010

In the present study, we proposed a new subspace scanning algorithm to enhance the spatial resolution of electroencephalography (EEG) and magnetoencephalography(MEG) source localization. Subspace scanning algorithms, represented by the multiple signal classification (MUSIC) algorithm and the first principal vector (FINE) algorithm, have been widely used to localize asynchronous multiple dipolar sources in human cerebral cortex. The conventional MUSIC algorithm used principal component analysis (PCA) to extract the noise vector subspace, thereby having difficulty in discriminating two or more closely-spaced cortical sources. The FINE algorithm addressed the problem by using only a part of the noise vector subspace, but there was no golden rule to determine the number of noise vectors. In the present work, we estimated a non-orthogonal signal vector set using independent component analysis (ICA) instead of using PCA and performed the source scanning process in the signal vector subspace, not in the noise vector subspace. Realistic 2D and 3D computer simulations, which compared the spatial resolutions of various algorithms under different noise levels, showed that the proposed ICA-MUSIC algorithm has the highest spatial resolution, suggesting that it can be a useful tool for practical EEG/MEG source localization.