• The Journal of the Acoustical Society of Korea
• /
• v.26 no.8
• /
• pp.390-396
• /
• 2007

In this letter, we propose a novel approach to improve the performance of speech/music classification for the selectable mode vocoder(SMV) of 3GPP2 using the Gaussian mixture model(GMM) which is based on the expectation-maximization(EM) algorithm. We first present an effective analysis of the features and the classification method adopted in the conventional SMV. And then feature vectors which are applied to the GMM are selected from relevant Parameters of the SMV for the efficient speech/music classification. The performance of the proposed algorithm is evaluated under various conditions and yields better results compared with the conventional scheme of the SMV.

• Economic and Environmental Geology
• /
• v.55 no.4
• /
• pp.353-366
• /
• 2022

Spatial estimation of geoscience data (geo-data) is challenging due to spatial heterogeneity, data scarcity, and high dimensionality. A novel spatial estimation method is needed to consider the characteristics of geo-data. In this study, we proposed the application of Gaussian Mixture Model (GMM) among machine learning algorithms with multivariate data for robust spatial predictions. The performance of the proposed approach was tested through soil chemical concentration data from a former smelting area. The concentrations of As and Pb determined by ex-situ ICP-AES were the primary variables to be interpolated, while the other metal concentrations by ICP-AES and all data determined by in-situ portable X-ray fluorescence (PXRF) were used as auxiliary variables in GMM and ordinary cokriging (OCK). Among the multidimensional auxiliary variables, important variables were selected using a variable selection method based on the random forest. The results of GMM with important multivariate auxiliary data decreased the root mean-squared error (RMSE) down to 0.11 for As and 0.33 for Pb and increased the correlations (r) up to 0.31 for As and 0.46 for Pb compared to those from ordinary kriging and OCK using univariate or bivariate data. The use of GMM improved the performance of spatial interpretation of anthropogenic metals in soil. The multivariate spatial approach can be applied to understand complex and heterogeneous geological and geochemical features.

• Speech Sciences
• /
• v.10 no.4
• /
• pp.149-157
• /
• 2003

In this paper, we proposed the principal component analysis (PCA) fuzzy mixture model for speaker identification. A PCA fuzzy mixture model is derived from the combination of the PCA and the fuzzy version of mixture model with diagonal covariance matrices. In this method, the feature vectors are first transformed by each speaker's PCA transformation matrix to reduce the correlation among the elements. Then, the fuzzy mixture model for speaker is obtained from these transformed feature vectors with reduced dimensions. The orthogonal Gaussian Mixture Model (GMM) can be derived as a special case of PCA fuzzy mixture model. In our experiments, with having the number of mixtures equal, the proposed method requires less training time and less storage as well as shows better speaker identification rate compared to the conventional GMM. Also, the proposed one shows equal or better identification performance than the orthogonal GMM does.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.6
• /
• pp.506-511
• /
• 2018

This paper proposes an GMM(Gaussian Mixture Model)-DNN(Deep Neural Network) hybrid-based feature compensation method for effective speech recognition in noisy environments. In the proposed algorithm, the posterior probability for the conventional GMM-based feature compensation method is calculated using DNN. The experimental results using the Aurora 2.0 framework and database demonstrate that the proposed GMM-DNN hybrid-based feature compensation method shows more effective in Known and Unknown noisy environments compared to the GMM-based method. In particular, the experiments of the Unknown environments show 9.13 % of relative improvement in the average of WER (Word Error Rate) and considerable improvements in lower SNR (Signal to Noise Ratio) conditions such as 0 and 5 dB SNR.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.3
• /
• pp.268-272
• /
• 2009

In this paper, we propose a Gaussian Mixture Model (GMM) based incremental robust adaptation with a forgetting factor for the speaker verification. Speaker recognition system uses a speaker model adaptation method with small amounts of data in order to obtain a good performance. However, a conventional adaptation method has vulnerable to the outlier from the irregular utterance variations and the presence noise, which results in inaccurate speaker model. As time goes by, a rate in which new data are adapted to a model is reduced. The proposed algorithm uses an incremental robust adaptation in order to reduce effect of outlier and use forgetting factor in order to maintain adaptive rate of new data on GMM based speaker model. The incremental robust adaptation uses a method which registers small amount of data in a speaker recognition model and adapts a model to new data to be tested. Experimental results from the data set gathered over seven months show that the proposed algorithm is robust against outliers and maintains adaptive rate of new data.

• Journal of Internet Computing and Services
• /
• v.5 no.3
• /
• pp.57-62
• /
• 2004

In this paper, an efficient speaker identification based on robust vector quantizationprincipal component analysis (VQ-PCA) is proposed to solve the problems from outliers and high dimensionality of training feature vectors in speaker identification, Firstly, the proposed method partitions the data space into several disjoint regions by roust VQ based on M-estimation. Secondly, the robust PCA is obtained from the covariance matrix in each region. Finally, our method obtains the Gaussian Mixture model (GMM) for speaker from the transformed feature vectors with reduced dimension by the robust PCA in each region, Compared to the conventional GMM with diagonal covariance matrix, under the same performance, the proposed method gives faster results with less storage and, moreover, shows robust performance to outliers.

• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1022-1027
• /
• 2020

In this paper, SVM-based speaker classification is experimented with GMM-supervector. To create a speaker cluster, conventional speaker change detection is performed with the KL distance using the SNR-based weighting function. SVM-based speaker classification consists of two steps. In the first step, SVM-based classification between UBM and speaker models is performed, speaker information is indexed in each cluster, and then grouped by speaker. In the second step, the SVM-based classification between UBM and speaker models is performed by inputting the speaker cluster group. Linear and RBF are applied as kernel functions for SVM-based classification. As a result, in the first step, the case of applying the linear kernel showed better performance than RBF with 148 speaker clusters, MDR 0, FAR 47.3, and ER 50.7. The second step experiment result also showed the best performance with 109 speaker clusters, MDR 1.3, FAR 28.4, and ER 32.1 when the linear kernel was applied.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.31-37
• /
• 2004

Wavelet transform is a useful tool for analysis and process of image. This showed good performance in image compression and noise reduction. Wavelet coefficients can be effectively modeled by hidden Markov tree(HMT) model. However, in application of HMT model to image interpolation, training procedure is needed. Moreover, the parameters obtained from training procedure do not match input image well. In this paper, the structure of HMT is used for image interpolation, and the parameters of HMT are obtained from statistical characteristics across wavelet subbands without training procedure. In the proposed method, wavelet coefficient is modeled as Gaussian mixture model(GMM). In GMM, state transition probabilities are determined from statistical transition characteristic of coefficient across subbands, and the variance of each state is estimated using the property of exponential decay of wavelet coefficient. In simulation, the proposed method shows improvement of performance compared with conventional bicubic method and the method using HMT model with training.

• Journal of the Korea Computer Graphics Society
• /
• v.26 no.5
• /
• pp.15-24
• /
• 2020

We present a supervised learning method that estimates the simulation parameters required to simulate the fabric from the static drape shape of a given fabric sample. The static drape shape was inspired by Cusick's drape, which is used in the apparel industry to classify fabrics according to their mechanical properties. The input vector of the training model consists of the feature vector extracted from the static drape and the density value of a fabric specimen. The output vector consists of six simulation parameters that have a significant influence on deriving the corresponding drape result. To generate a plausible and unbiased training data set, we first collect simulation parameters for 400 knit fabrics and generate a Gaussian Mixed Model (GMM) generation model from them. Next, a large number of simulation parameters are randomly sampled from the GMM model, and cloth simulation is performed for each sampled simulation parameter to create a virtual static drape. The generated training data is fitted with a log-linear regression model. To evaluate our method, we check the accuracy of the training results with a test data set and compare the visual similarity of the simulated drapes.

• 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.