• Proceedings of the Korea Information Processing Society Conference
• /
• 2012.11a
• /
• pp.148-151
• /
• 2012

범용 GPU (general-purpose computing on graphics processing units, GPGPU)는 GPU를 일반적인 목적으로 사용하고자 하는 병렬 컴퓨터 구조로써, 과학 연산 등 여러 분야에서 응용 프로그램의 성능을 향상시키기 위하여 사용되고 있다. 본 연구에서는 음성인식기에서 주로 사용되는 가우시안 혼합 모델(Gaussian mixture model, GMM)에서 많은 연산시간을 차지하는 관측확률 계산의 성능을 향상시키고자 GPGPU를 이용하는 알고리즘을 구현하였으며, 기존 CPU 기반 알고리즘 대비 약 13배 연산시간을 단축하였다.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.6
• /
• pp.473-480
• /
• 2004

In this paper we propose an effective feature compensation scheme based on the speech model in order to achieve robust speech recognition. The proposed feature compensation method is based on parallel combined mixture model (PCMM). The previous PCMM works require a highly sophisticated procedure for estimation of the combined mixture model in order to reflect the time-varying noisy conditions at every utterance. The proposed schemes can cope with the time-varying background noise by employing the interpolation method of the multiple mixture models. We apply the‘data-driven’method to PCMM tot move reliable model combination and introduce a frame-synched version for estimation of environments posteriori. In order to reduce the computational complexity due to multiple models, we propose a technique for mixture sharing. The statistically similar Gaussian components are selected and the smoothed versions are generated for sharing. The performance is examined over Aurora 2.0 and speech corpus recorded while car-driving. The experimental results indicate that the proposed schemes are effective in realizing robust speech recognition and reducing the computational complexities under both simulated environments and real-life conditions.

• Journal of Korea Multimedia Society
• /
• v.15 no.6
• /
• pp.748-760
• /
• 2012

In case brightness distribution is concentrated in a region, it is difficult to classify the image features. To solve this problem, we apply global histogram equalization and local histogram equalization to images. In case of global histogram equalization, it can be too bright or dark because it doesn't consider the density of brightness distribution. Thus, it is difficult to enhance the local contrast in the images. In case of local histogram equalization, it can produce unexpected blocks in the images. In order to enhance the contrast in the images, this paper proposes a local histogram equalization based on the Gaussian Mixture Models(GMMs) in regions of histogram. Mean and variance parameters in each regions is updated EM-algorithm repeatedly and then ranges of equalization on each regions. The experimental results performed with image of various contrasts show that the proposed algorithm is better than the global histogram equalization.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.1
• /
• pp.22-29
• /
• 2010

A real-time detection and tracking of moving objects in video sequences is very important for smart surveillance systems. In this paper, we propose a novel algorithm for the detection of moving objects that is the entropy-based adaptive Gaussian mixture model (AGMM). First, the increment of entropy generally means the increment of complexity, and objects in unstable conditions cause higher entropy variations. Hence, if we apply these properties to the motion segmentation, pixels with large changes in entropy in moments have a higher chance in belonging to moving objects. Therefore, we apply the Clausius entropy theory to convert the pixel value in an image domain into the amount of energy change in an entropy domain. Second, we use an adaptive background subtraction method to detect moving objects. This models entropy variations from backgrounds as a mixture of Gaussians. Experiment results demonstrate that our method can detect motion object effectively and reliably.

• Smart Media Journal
• /
• v.4 no.4
• /
• pp.18-23
• /
• 2015

In this paper, we propose a method for detecting the number of clusters. This method can improve the performance of a gaussian mixture model function in conventional markov random field method by using the tensor voting. The key point of the proposed method is that extracts the number of the center through the continuity of saliency map of the input data of the tensor voting token. At first, we separate the foreground and background region candidate in a given natural images. After that, we extract the appropriate cluster number for each separate candidate regions by applying the tensor voting. We can make accurate modeling a gaussian mixture model by using a detected number of cluster. We can return the result of natural binary text image by calculating the unary term and the pairwise term of markov random field. After the experiment, we can confirm that the proposed method returns the optimal cluster number and text binarization results are improved.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.3
• /
• pp.396-402
• /
• 2021

As the world is trying to establish smart city, unmanned vehicle control systems are being widely used. This paper writes about an unmanned parking control system that uses an adaptive background image modeling method, suggesting the method of updating the background image, modeled with an adaptive Gaussian mixture model, in both global and local way according to the moving object. Specifically, this paper focuses on suggesting two methods; a method of minimizing the influence of a moving object on a background image and a method of accurately updating the background image by quickly removing afterimages of moving objects within the area of interest to be monitored. In this paper, through the implementation of the unmanned vehicle control system, we proved that the proposed system can quickly and accurately distinguish both moving and static objects such as vehicles from the background image.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.3
• /
• pp.141-149
• /
• 2005

Tn general. Gaussian mixture model (GMM) is used to estimate the speaker model from the speech for speaker identification. The parameter estimates of the GMM are obtained by using the Expectation-Maximization (EM) algorithm for the maximum likelihood (ML) estimation. However the EM algorithm has such drawbacks that it depends heavily on the initialization and it needs the number of mixtures to be known. In this paper, to solve the above problems of the EM algorithm. we propose an EM algorithm with the initialization based on incremental ${\cal}k-means$ for GMM. The proposed method dynamically increases the number of mixtures one by one until finding the optimum number of mixtures. Whenever adding one mixture, we calculate the mutual relationship between it and one of other mixtures respectively. Finally. based on these mutual relationships. we can estimate the optimal number of mixtures which are statistically independent. The effectiveness of the proposed method is shown by the experiment for artificial data. Also. we performed the speaker identification by applying the proposed method comparing with other approaches.

• Journal of Broadcast Engineering
• /
• v.23 no.4
• /
• pp.511-518
• /
• 2018

This paper deals with improving speech intelligibility by applying binary mask to time-frequency units of speech in noise. The binary mask is set to "0" or "1" according to whether speech is dominant or noise is dominant by comparing signal-to-noise ratio with pre-defined threshold. Bayesian classifier trained with Gaussian mixture model is used to estimate the binary mask of each time-frequency signal. The binary mask based noise suppressor improves speech intelligibility only in noise condition which is included in the training data. In this paper, speaker adaptation techniques for speech recognition are applied to adapt the Gaussian mixture model to a new noise environment. Experiments with noise-corrupted speech are conducted to demonstrate the improvement of speech intelligibility by employing adaption techniques in a new noise environment.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.3
• /
• pp.119-128
• /
• 2008

This paper analyzes the relationship between two representative statistical methods for bandwidth extension (BWE): Gaussian Mixture Model (GMM) and Hidden Markov Model (HMM) ones, and compares their performances. The HMM method is a memory-based system which was developed to take advantage of the inter-frame dependency of speech signals. Therefore, it could be expected to estimate better the transitional information of the original spectra from frame to frame. To verify it, a dynamic measure that is an approximation of the 1st-order derivative of spectral function over time was introduced in addition to a static measure. The comparison result shows that the two methods are similar in the static measure, while, in the dynamic measure, the HMM method outperforms explicitly the GMM one. Moreover, this difference increases in proportion to the number of states of HMM model. This indicates that the HMM method would be more appropriate at least for the 'blind BWE' problem. On the other hand, nevertheless, the GMM method could be treated as a preferable alternative of the HMM one in some applications where the static performance and algorithm complexity are critical.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.11a
• /
• pp.283-289
• /
• 2005

Background Subtraction은 움직이는 물체 검출에 가장 많이 사용되는 방법 중 하나이다. 배경이 복잡하고 변화가 심한 경우, 배경을 실시간으로 얼마나 정확하게 학습하는가가 물체 검출의 정확도를 결정한다. Gaussian Mixture Model은 이러한 배경의 모델링에 가장 많이 쓰이는 방법이다. Gaussian Mixture Model은 확률적 학습 방법을 사용하는데, 이러한 방법은 물체가 자주 지나다니거나 물체가 멈춰있는 경우, 배경을 정확하게 모델링하지 못한다. 본 논문에서는 밝기 값에 대한 확률적 모델링과 밝기 값의 변화에 따른 처리를 결합하여 혼잡한 환경에서 배경을 정확하게 모델링할 수 있는 학습 방법을 제안한다.