• The Journal of the Acoustical Society of Korea
• /
• v.30 no.3
• /
• pp.123-128
• /
• 2011

In this paper, we propose the improved noise power estimation in speech enhancement under various noise environments. The previous MS algorithm tracking the minimum value of finite search window uses the optimal power spectrum of signal for smoothing and adopts minimum probability. From the investigation of the previous MS-based methods it can be seen that a fixed size of the minimum search window is assumed regardless of the various environment. To achieve the different search window size, we use the noise classification algorithm based on the Gaussian mixture model (GMM). Performance of the proposed enhancement algorithm is evaluated by ITU-T P.862 perceptual evaluation of speech quality (PESQ) under various noise environments. Based on this, we show that the proposed algorithm yields better result compared to the conventional MS method.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.7 no.5
• /
• pp.967-974
• /
• 2012

In this paper, a vehicle detection algorithm with HD CCTV camera images using GMM(Gaussian Mixture Model) algorithm and mathematical morphological processing is proposed. At the first stage, background could be estimated using GMM from CCTV input image signal and then object could be separated from difference image of the input image and background image. At the second stage, candidated object were reformed by using mathematical morphological processing. Finally, vehicle object could be detected using vehicle size informations depend on distance and vehicle type in tunnel. Through real experiments in tunnel, it is shown that the proposed system works well.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.46 no.4
• /
• pp.76-81
• /
• 2009

We propose an effective emotion recognition algorithm based on the minimum classification error (MCE) incorporating multi-modal system The emotion recognition is performed based on a Gaussian mixture model (GMM) based on MCE method employing on log-likelihood. In particular, the reposed technique is based on the fusion of feature vectors based on voice signal and galvanic skin response (GSR) from the body sensor. The experimental results indicate that performance of the proposal approach based on MCE incorporating the multi-modal system outperforms the conventional approach.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.6 s.38
• /
• pp.187-194
• /
• 2005

The background subtraction method is mainly used for the real-time extraction and tracking of moving objects from image sequences. In the outdoor environment, there are many changeable environment factors such as gradually changing illumination, swaying trees and suddenly moving objects , which are to be considered for an adaptive processing. Normally, GMM(Gaussian Mixture Model) is used to subtract the background by considering adaptively the various changes in the scenes, and the adaptive GMMs improving the real-time Performance were Proposed and worked. This paper, for on-line background subtraction, employed the improved adaptive GMM, which uses the small constant for learning rate a and is not able to speedily adapt the suddenly movement of objects, So, this paper Proposed and evaluated the dynamic control method of a using the adaptive selection of the number of component distributions and the global variances of pixel values.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.9
• /
• pp.939-945
• /
• 2009

In this paper, we proposed a method which corresponds people under the structured spaces with multiple cameras. The correspondence takes an important role for using multiple camera system. For solving this correspondence, the proposed method consists of three main steps. Firstly, moving objects are detected by background subtraction using a multiple background model. The temporal difference is simultaneously used to reduce a noise in the temporal change. When more than two people are detected, those detected regions are divided into each label to represent an individual person. Secondly, the detected region is segmented as features for correspondence by a criterion with the color distribution and context information of human body. The segmented region is represented as a set of blobs. Each blob is described as Gaussian probability distribution, i.e., a person model is generated from the blobs as a Gaussian Mixture Model (GMM). Finally, a GMM of each person from a camera is matched with the model of other people from different cameras by maximum likelihood. From those results, we identify a same person in different view. The experiment was performed according to three scenarios and verified the performance in qualitative and quantitative results.

• Journal of Information Processing Systems
• /
• v.14 no.4
• /
• pp.807-823
• /
• 2018

Speaker verification system performance depends on the utterance of each speaker. To verify the speaker, important information has to be captured from the utterance. Nowadays under the constraints of limited data, speaker verification has become a challenging task. The testing and training data are in terms of few seconds in limited data. The feature vectors extracted from single frame size and rate (SFSR) analysis is not sufficient for training and testing speakers in speaker verification. This leads to poor speaker modeling during training and may not provide good decision during testing. The problem is to be resolved by increasing feature vectors of training and testing data to the same duration. For that we are using multiple frame size (MFS), multiple frame rate (MFR), and multiple frame size and rate (MFSR) analysis techniques for speaker verification under limited data condition. These analysis techniques relatively extract more feature vector during training and testing and develop improved modeling and testing for limited data. To demonstrate this we have used mel-frequency cepstral coefficients (MFCC) and linear prediction cepstral coefficients (LPCC) as feature. Gaussian mixture model (GMM) and GMM-universal background model (GMM-UBM) are used for modeling the speaker. The database used is NIST-2003. The experimental results indicate that, improved performance of MFS, MFR, and MFSR analysis radically better compared with SFSR analysis. The experimental results show that LPCC based MFSR analysis perform better compared to other analysis techniques and feature extraction techniques.

• MALSORI
• /
• no.64
• /
• pp.77-88
• /
• 2007

Nowadays, mel-frequency cesptral coefficients (MFCCs) and Gaussian mixture models (GMMs) are used for the pathological voice detection. This paper suggests a method to improve the performance of the pathological/normal voice classification based on the MFCC-based GMM. We analyze the characteristics of the mel frequency-based filterbank energies using the fisher discriminant ratio (FDR). And the feature vectors through the linear discriminant analysis (LDA) transformation of the filterbank energies (FBE) and the MFCCs are implemented. An accuracy is measured by the GMM classifier. This paper shows that the FBE LDA-based GMM is a sufficiently distinct method for the pathological/normal voice classification, with a 96.6% classification performance rate. The proposed method shows better performance than the MFCC-based GMM with noticeable improvement of 54.05% in terms of error reduction.

• Phonetics and Speech Sciences
• /
• v.7 no.3
• /
• pp.131-138
• /
• 2015

In this paper, we propose L1-norm regularization for state vector adaptation of subspace Gaussian mixture model (SGMM). When you design a speaker adaptation system with GMM-HMM acoustic model, MAP is the most typical technique to be considered. However, in MAP adaptation procedure, large number of parameters should be updated simultaneously. We can adopt sparse adaptation such as L1-norm regularization or sparse MAP to cope with that, but the performance of sparse adaptation is not good as MAP adaptation. However, SGMM does not suffer a lot from sparse adaptation as GMM-HMM because each Gaussian mean vector in SGMM is defined as a weighted sum of basis vectors, which is much robust to the fluctuation of parameters. Since there are only a few adaptation techniques appropriate for SGMM, our proposed method could be powerful especially when the number of adaptation data is limited. Experimental results show that error reduction rate of the proposed method is better than the result of MAP adaptation of SGMM, even with small adaptation data.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.16 no.9
• /
• pp.1870-1877
• /
• 2012

Transient signals generally have short duration and variable length with time-varying and non-stationary characteristics. Thus frame-based pattern matching method is useful for classification of transient signals. In this paper, we propose a new method for classification of underwater transient signals using a Gaussian mixture model(GMM). We carried out classification experiments for various underwater transient signals depending upon the types of noise, signal-to-noise ratio, and number of mixtures in the GMM. Experimental results have verified that the proposed method works quite well for classification of underwater transient signals.

• Journal of Information Processing Systems
• /
• v.9 no.4
• /
• pp.592-601
• /
• 2013

Object segmentation is a challenging task in image processing and computer vision. In this paper, we present a visual attention based segmentation method to segment small sized interesting objects in natural images. Different from the traditional methods, we first search the region of interest by using our novel saliency-based method, which is mainly based on band-pass filtering, to obtain the appropriate frequency. Secondly, we applied the Gaussian Mixture Model (GMM) to locate the object region. By incorporating the visual attention analysis into object segmentation, our proposed approach is able to narrow the search region for object segmentation, so that the accuracy is increased and the computational complexity is reduced. The experimental results indicate that our proposed approach is efficient for object segmentation in natural images, especially for small objects. Our proposed method significantly outperforms traditional GMM based segmentation.