This paper proposes a novel approach that combines statistical models and support vector machines. A hybrid scheme which appropriately incorporates the advantages of both the generative and discriminant model paradigms is described and evaluated. Support vector machines (SVMs) are trained to divide the whole speakers’ space into small subsets of speakers within a hierarchical tree structure. Du...

Statistical classifiers operate on features that generally include both useful and useless information. These two types of information are difficult to separate in the feature domain. Recently, a new paradigm based on a Latent Factor Analysis (LFA) proposed a model decomposition into usefull and useless components. This method was successfully applied to speaker and language recognition tasks. ...

In this paper, we present a new method for isolated keyword detection that is meant to activate a personal device from standby state. Instead of using the common method for speech recognition such as Hidden Markov Model (HMM) or Dynamic Time Warping (DTW), we modify a GMM-UBM (Gaussian Mixture Model – Universal Background Model) scheme that is better known in speaker recognition field. Since on...

An automated method of MR brain image segmentation is presented. A block based Expectation Maximization Algorithm is proposed for the tissue classification of MR brain images. The standard Gaussian Mixture Model is the most widely used method for MR Brain image segmentation and Expectation Maximization algorithm is used to estimate the model parameters. The Gaussian Mixture Model considers each...

In this paper, we propose a novel boosted mixture learning (BML) framework for Gaussian mixture HMMs in speech recognition. BML is an incremental method to learn mixture models for classification problem. In each step of BML, one new mixture component is calculated according to functional gradient of an objective function to ensure that it is added along the direction to maximize the objective ...

While block transform image coding has not been very popular lately in the presence of current state-of-the-art wavelet-based coders, the Gaussian mixture model (GMM)-based block quantiser, without the use of entropy coding, is still very competitive in the class of fixed rate transform coders. In this paper, a GMM-based block quantiser of low computational complexity is presented which is base...

Traditional subspace based speech enhancement (SSE) methods use linear minimum mean square error (LMMSE) estimation that is optimal if the Karhunen Loeve transform (KLT) coefficients of speech and noise are Gaussian distributed. In this paper, we investigate the use of Gaussian mixture (GM) density for modeling the non-Gaussian statistics of the clean speech KLT coefficients. Using Gaussian mix...

Moving object detection is critical task in video analytics. Gaussian Mixture Model (GMM) based background subtraction is widely popular technique for moving object detection due to its robustness to multimodality and lighting changes. This paper presents the critical survey about various GMM based approaches for handling critical background situations. This survey describes various challenges ...

This thesis devises quantization and source-channel coding schemes to increase the error robustness of the newly standardized ITU-T G.711.1 speech coder. The schemes employ Gaussian mixture model (GMM) based multiple description quantizers (MDQ). The thesis reviews the literature focusing on GMM based quantization, MDQ, and GMM-MDQ design methods and bit allocation schemes. GMM-MDQ are then des...

Gaussian Mixture Model (GMM) computation is known to be one of the most computation-intensive components in speech decoding. In our previous work, context-independent model based GMM selection (CIGMMS) was found to be an effective way to reduce the cost of GMM computation without significant loss in recognition accuracy. In this work, we propose three methods to further improve the performance ...