This paper presents a novel training algorithm for Hidden Markov Model (HMM)-based speech synthesis. One of the biggest issues causing significant quality degradation in synthetic speech is the over-smoothing effect often observed in generated speech parameter trajectories. Recently, we have found that a Modulation Spectrum (MS) of the generated speech parameters is sensitively correlated with ...

  In this paper, we review novel techniques in the emerging field of spatiotemporal 4D PET imaging. We will discuss existing limitations in conventional dynamic PET imaging which involves independent reconstruction of dynamic PET datasets. Various approaches that seek to attempt some or all of these limitations are reviewed in this work, including techniques that util...

We consider the use of generalized additive models with correlated errors for analysing trends in time series. The trend is represented as a smoothing spline so that it can be extrapolated. A method is proposed for choosing the smoothing parameter. It is based on the ability to predict a short term into the future. The choice not only addresses the purpose in hand, but also performs very well, ...

The dynamic Nash equilibrium problem with shared constraints (NEPSC) involves a dynamic decision process withmultiple players, where not only the players’ cost functionals but also their admissible control sets depend on the rivals’ decision variables through shared constraints. For a class of the dynamic NEPSC, we propose a differential variational inequality formulation. Using this formulatio...

In this paper, we address the problem of risk-sensitive tiitering and smoothing for discrete-time Hidden Markov Models (HMM ) with finite-discrete states. The objective of risk-sensitive tiltering is to minimise the expectation of the exponential of the squared estimation error weighted by a risk-sensitive parameter. Wc use the so-called Reference Probability Method in solving this problem. We ...

We propose a new GMM criterion for models defined by conditional moment restrictions based on local averaging. It resembles a statistic based on smoothing techniques used in specification testing. Depending on whether the smoothing parameter is fixed or decreases to zero with the sample size, our approach defines a whole class of estimators. We show that consistency and asymptotic normality fol...

In nonparametric curve estimation the decision about the type of smoothing parameter is critical for the practical performance. The nearest neighbor bandwidth as introduced by Gefeller and Dette 1992 for censored data in survival analysis is specified by one parameter, namely the number of nearest neighbors. Bandwidth selection in this setting is rarely investigated although not linked closely ...