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.

DT-MRI data visualisation using the dual tree Complex Wavelet transform

In this paper a novel visualisation method for diffusion tensor MRI datasets is introduced. This is based on the use of Complex Wavelets in order to produce "stripy" textures which depict the anisotropic component of the diffusion tensors. Grey-scale pixel intensity is used to show the isotropic component. This paper also discusses enhancements of the technique for 3D visualisation. © 2004 IEEE.

Which diagrams and when? Health workers' choice and usage of different diagram types for service improvement

Diagrammatic representations, such as process mapping and care pathways, have been often used for service evaluation and improvement in healthcare. While a broad range of diagrammatic representations exist, their application in healthcare has been very limited. There is a lack of understanding about how and which diagrams could be usable and useful to health workers. In this study, ten mental health workers were asked to discuss positive and negative issues around their service delivery using one or two diagrams of their choice out of seven different diagrams representing their service: care pathway diagram; organisation diagram; communication diagram; service blueprint; patient state transition diagram; free form diagram; geographic map. Their interactions with diagrams were video-taped for analysis. The patient state transition diagram was the most popular choice in spite of relatively low previous familiarity. The overall findings provided insight into a better use of diagrams in healthcare. © 2012 Springer-Verlag.

Making a shallow network deep: Conversion of a boosting classifier into a decision tree by boolean optimisation

This paper presents a novel way to speed up the evaluation time of a boosting classifier. We make a shallow (flat) network deep (hierarchical) by growing a tree from decision regions of a given boosting classifier. The tree provides many short paths for speeding up while preserving the reasonably smooth decision regions of the boosting classifier for good generalisation. For converting a boosting classifier into a decision tree, we formulate a Boolean optimization problem, which has been previously studied for circuit design but limited to a small number of binary variables. In this work, a novel optimisation method is proposed for, firstly, several tens of variables i.e. weak-learners of a boosting classifier, and then any larger number of weak-learners by using a two-stage cascade. Experiments on the synthetic and face image data sets show that the obtained tree achieves a significant speed up both over a standard boosting classifier and the Fast-exit-a previously described method for speeding-up boosting classification, at the same accuracy. The proposed method as a general meta-algorithm is also useful for a boosting cascade, where it speeds up individual stage classifiers by different gains. The proposed method is further demonstrated for fast-moving object tracking and segmentation problems. © 2011 Springer Science+Business Media, LLC.

Multiple classifier boosting and tree-structured classifiers

Visual recognition problems often involve classification of myriads of pixels, across scales, to locate objects of interest in an image or to segment images according to object classes. The requirement for high speed and accuracy makes the problems very challenging and has motivated studies on efficient classification algorithms. A novel multi-classifier boosting algorithm is proposed to tackle the multimodal problems by simultaneously clustering samples and boosting classifiers in Section 2. The method is extended into an online version for object tracking in Section 3. Section 4 presents a tree-structured classifier, called Super tree, to further speed up the classification time of a standard boosting classifier. The proposed methods are demonstrated for object detection, tracking and segmentation tasks. © 2013 Springer-Verlag Berlin Heidelberg.

Angle-of-attack effects on counter-rotating propellers at take-off

Due to their potential for significant fuel consumption savings, Counter-Rotating Open Rotors (CRORs) are currently being considered as an alternative to high-bypass turbofans. When CRORs are mounted on an aircraft, several 'installation effects' arise which are not present when the engine is operated in isolation. This paper investigates how flow features arising from one such effect - The angle-of-attack of the engine centre-line relative to the oncoming flow - can influence the design of CROR engines. Three-dimensional full-annulus unsteady CFD simulations are used to predict the time-varying flow field experienced by each rotor and emphasis is put on the interaction of the frontrotor wake and tip vortex with the rear-rotor. A parametric study is presented that quantifies the rotorrotor interaction as a function of the angle-of-attack. It is shown that angle-of-attack operation significantly changes the flow field and the unsteady lift on both rotors. In particular, a frequency analysis shows that the unsteady lift exhibits sidebands around the rotor-rotor interaction frequencies. Further, a non-linear increase in the total rear-rotor tip unsteadiness is observed for moderate and high angles-of-attack. The results presented in this paper demonstrate that common techniques used to mitigate CROR noise, such as modifying the rotor-rotor axial spacing and rear-rotor crop, can not be applied correctly unless angle-of-attack effects are taken into account. Copyright © 2012 by ASME.

A condensation particle counter insensitive to volatile particles

A High Temperature Condensation Particle Counter (HT-CPC) is described that operates at an elevated temperature of up to ca. 300. °C such that volatile particles from typical combustion sources are not counted. The HT-CPC is functionally identical to a conventional CPC, the main challenge being to find suitable non-hazardous working fluids, with good stability, and an appropriate vapour pressure. Some key design features are described, and results of modelling which predict the HT-CPC counting efficiency. Experimental results are presented for several candidate fluids when the HT-CPC was challenged with ambient, NaCl and diesel soot particles, and the results show good agreement with modelled predictions, and confirm that counting of particles of diameters down to at least 10. nm was achievable. Possible applications are presented, including measurement of particles from a diesel car engine and comparison with a near PMP system. © 2014 Elsevier Ltd.

Dense active appearance models using a bounded diameter minimum spanning tree

We present a method for producing dense Active Appearance Models (AAMs), suitable for video-realistic synthesis. To this end we estimate a joint alignment of all training images using a set of pairwise registrations and ensure that these pairwise registrations are only calculated between similar images. This is achieved by defining a graph on the image set whose edge weights correspond to registration errors and computing a bounded diameter minimum spanning tree (BDMST). Dense optical flow is used to compute pairwise registration and we introduce a flow refinement method to align small scale texture. Once registration between training images has been established we propose a method to add vertices to the AAM in a way that minimises error between the observed flow fields and a flow field interpolated between the AAM mesh points. We demonstrate a significant improvement in model compactness using the proposed method and show it dealing with cases that are problematic for current state-of-the-art approaches.