The most successful systems in previous comparative studies on speaker age recognition used short-term cepstral features modeled with Gaussian Mixture Models (GMMs) or applied multiple phone recognizers trained with the data of speakers of the respective class. Acoustic analyses, however, indicate that certain features such as pitch extracted from a longer span of speech correlate clearly with ...

A new framework for time domain voiced phoneme recognition is shown. Each speech frame taken for training and recognition is bounded by consecutive glottal closures. A preprocessing stage is designed and implemented to model pitch synchronous frames with gaussian mixture models. Component analysis carried out on the data shows optimal performance with a very small number of components, requirin...

This paper describes the Nuance–Politecnico di Torino (NPT) speaker recognition system submitted to the NIST SRE12 evaluation campaign. Included are the results of postevaluation tests, focusing on the analysis of the effects of score normalization and condition-dependent calibration. The submitted system combines the results of five acoustic recognizers all based on Gaussian Mixture Models (GM...

This paper presents a statistical approach to aggregating speed and phase (directional) information for vascular segmentation in phase contrast magnetic resonance angiograms (PC-MRA), and proposes a Maxwell-Gaussian finite mixture distribution to model the background noise distribution. In this paper, we extend our previous work [6] to the segmentation of phase-difference PC-MRA speed images. W...

Several popular classification algorithms used to segment magnetic resonance brain images assume that the image intensities, or log-transformed intensities, satisfy a finite Gaussian mixture model. In these methods, the parameters of the mixture model are estimated and the posterior probabilities for each tissue class are used directly as soft segmentations or combined to form a hard segmentati...

Image segmentation is an important problem which addresses the needs of lots of biomedical applications. In this work, we adress the problem with MRF-coupled mixture models. In the standard finite mixture models, the number of segments that we are supposed to find in an image is fixed. With the Bayesian non-parametrics formulation we automatically find the number of segments by considering an i...

Positive Data Clustering Using Finite Inverted Dirichlet Mixture Models Taoufik BDIRI In this thesis we present an unsupervised algorithm for learning finite mixture models from multivariate positive data. Indeed, this kind of data appears naturally in many applications, yet it has not been adequately addressed in the past. This mixture model is based on the inverted Dirichlet distribution, whi...

In Speaker Identification the goal is to determine which one of a group of a known voice with best matches with the one of the input voices. Modelling the speaker voices is an important consideration for many applications. In developing the model, it is customary to consider that the voice of the individual speaker is characterized with finite component Gaussian mixture model. However, the Mel ...

This paper is concerned with estimating a probability density function of human skin color using a finite Gaussian mixture model whose parameters are estimated through the EM algorithm. There are no limitations regarding if person is black or white. Two important sections of Gaussian mixture are parameter estimation and determining the number of mixture components. Experimental results show tha...