No abstract

This paper presents a voice conversion technique based on bilinear models and introduces the concept of contextual modeling. The bilinear approach reformulates the spectral envelope representation from line spectral frequencies feature to a two-factor parameterization corresponding to speaker identity and phonetic information, the so-called style and content factors. This decomposition offers a flexible representation suitable for voice conversion and facilitates the use of efficient training algorithms based on singular value decomposition. In a contextual approach (bilinear) models are trained on subsets of the training data selected on the fly at conversion time depending on the characteristics of the feature vector to be converted. The performance of bilinear models and context modeling is evaluated in objective and perceptual tests by comparison with the popular GMM-based voice conversion method for several sizes and different types of training data

Abstract. In this paper, we propose a new method for underdetermined blind source separation of reverberant speech mixtures by classifying each time-frequency (T-F) point of the mixtures according to a combined variational Bayesian model of spatial cues, under sparse signal representation assumption. We model the T-F observations by a variational mixture of circularly-symmetric complex-Gaussians. The spatial cues, e.g. interaural level difference (ILD), interaural phase difference (IPD) and mixing vector cues, are modelled by a variational mixture of Gaussians. We then establish appropriate conjugate prior distributions for the parameters of all the mixtures to create a variational Bayesian framework. Using the Bayesian approach we then iteratively estimate the hyper-parameters for the prior distributions by optimizing the variational posterior distribution. The main advantage of this approach is that no prior knowledge of the number of sources is needed, and it will be automatically determined by the algorithm. The proposed approach does not suffer from overfitting problem, as opposed to the Expectation-Maximization (EM) algorithm, therefore it is not sensitive to initializations.

Abstract:The paper presents the system WSC, designed to provide modeling, organization, management and execution of Web services. The Service and Community ontologies are used for modeling of the Web services and Web services communities. Web Services are organized in semantic communities, in order to be easily accessed. Thus, the users of system navigate through the taxonomy of communities and invoke the target generic operations of communities. If an invoked operation requires some pre-operations to be executed before it, the system builds process diagram for these pre-operations. The user executes interactively each operation of diagram process using the interface provided by the system.

No abstract