Unsupervised intra-lingual and cross-lingual speaker adaptation for HMM-based speech synthesis using two-pass decision tree construction

Hidden Markov model (HMM)-based speech synthesis systems possess several advantages over concatenative synthesis systems. One such advantage is the relative ease with which HMM-based systems are adapted to speakers not present in the training dataset. Speaker adaptation methods used in the field of HMM-based automatic speech recognition (ASR) are adopted for this task. In the case of unsupervised speaker adaptation, previous work has used a supplementary set of acoustic models to estimate the transcription of the adaptation data. This paper first presents an approach to the unsupervised speaker adaptation task for HMM-based speech synthesis models which avoids the need for such supplementary acoustic models. This is achieved by defining a mapping between HMM-based synthesis models and ASR-style models, via a two-pass decision tree construction process. Second, it is shown that this mapping also enables unsupervised adaptation of HMM-based speech synthesis models without the need to perform linguistic analysis of the estimated transcription of the adaptation data. Third, this paper demonstrates how this technique lends itself to the task of unsupervised cross-lingual adaptation of HMM-based speech synthesis models, and explains the advantages of such an approach. Finally, listener evaluations reveal that the proposed unsupervised adaptation methods deliver performance approaching that of supervised adaptation.

A controller for a miniature intra-aortic ventricular assist device.

Two control algorithms have been developed for a minimally invasive axial-flow ventricular assist device (VAD) for placement in the descending aorta. The purpose of the device is to offload the left ventricle and to augment lower body perfusion in patients with moderate congestive heart failure. The VAD consists of an intra-aortic impeller with a built-in permanent magnet rotor and an extra-aortic stator. The control algorithms, which use pressure readings upstream and downstream of the VAD to determine the pump status, have been tested in a mock circulatory system under two conditions, namely with or without afterload sensitivity. The results give an insight into controller design for an intra-aortic blood pump working in series with the heart.

Design method of an innovative motor for an intra-aortic ventricular assist device

A permanent-magnet motor has been designed for an innovative axial-flow ventricular assist device (VAD), to be placed in the descending aorta, intended to offload the left ventricle and augment renal perfusion in patients with congestive heart failure (CHF). For this application, an intra-aortic impeller with a built-in permanent magnet rotor is driven by an extraaortic stator working in synchronism with the natural heart. To meet this need, a two-dimensional analytical model has been developed in the MATLAB environment to estimate machine parameters; finite element analysis (FEA) has been used to refine the results. A prototype blood pump equipped with an innovative motor designed from the procedure above has been tested in a mock loop representing the human circulatory system. The performance of VAD incorporating the motor is presented. © 2009 IEEE.

Measuring the compressive viscoelastic mechanical properties of human cervical tissue using indentation.

The human cervix is an important mechanical barrier in pregnancy which must withstand the compressive and tensile forces generated from the growing fetus. Premature cervical shortening resulting from premature cervical remodeling and alterations of cervical material properties are known to increase a woman׳s risk of preterm birth (PTB). To understand the mechanical role of the cervix during pregnancy and to potentially develop indentation techniques for in vivo diagnostics to identify women who are at risk for premature cervical remodeling and thus preterm birth, we developed a spherical indentation technique to measure the time-dependent material properties of human cervical tissue taken from patients undergoing hysterectomy. In this study we present an inverse finite element analysis (IFEA) that optimizes material parameters of a viscoelastic material model to fit the stress-relaxation response of excised tissue slices to spherical indentation. Here we detail our IFEA methodology, report compressive viscoelastic material parameters for cervical tissue slices from nonpregnant (NP) and pregnant (PG) hysterectomy patients, and report slice-by-slice data for whole cervical tissue specimens. The material parameters reported here for human cervical tissue can be used to model the compressive time-dependent behavior of the tissue within a small strain regime of 25%.