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.

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.

Modification of the trapped field in bulk high-temperature superconductors as a result of the drilling of a pattern of artificial columnar holes

The trapped magnetic field is examined in bulk high-temperature superconductors that are artificially drilled along their c-axis. The influence of the hole pattern on the magnetization is studied and compared by means of numerical models and Hall probe mapping techniques. To this aim, we consider two bulk YBCO samples with a rectangular cross-section that are drilled each by six holes arranged either on a rectangular lattice (sample I) or on a centered rectangular lattice (sample II). For the numerical analysis, three different models are considered for calculating the trapped flux: (i), a two-dimensional (2D) Bean model neglecting demagnetizing effects and flux creep, (ii), a 2D finite-element model neglecting demagnetizing effects but incorporating magnetic relaxation in the form of an E-J power law, and, (iii), a 3D finite element analysis that takes into account both the finite height of the sample and flux creep effects. For the experimental analysis, the trapped magnetic flux density is measured above the sample surface by Hall probe mapping performed before and after the drilling process. The maximum trapped flux density in the drilled samples is found to be smaller than that in the plain samples. The smallest magnetization drop is found for sample II, with the centered rectangular lattice. This result is confirmed by the numerical models. In each sample, the relative drops that are calculated independently with the three different models are in good agreement. As observed experimentally, the magnetization drop calculated in the sample II is the smallest one and its relative value is comparable to the measured one. By contrast, the measured magnetization drop in sample (1) is much larger than that predicted by the simulations, most likely because of a change of the microstructure during the drilling process.

Measurement of the magnetic field inside the holes of a drilled bulk high-Tc superconductor

We use macroscopic holes drilled in a bulk YBCO superconductor to probe its magnetic properties in the volume of the sample. The sample is subjected to an AC magnetic flux with a density ranging from 30mT to 130mT and the flux in the superconductor is probed by miniature coils inserted in the holes. In a given hole, three different penetration regimes can be observed: (i) the shielded regime, where no magnetic flux threads the hole; (ii) the gradual penetration regime, where the waveform of the magnetic field has a clipped sine shape whose fundamental component scales with the applied field; and (iii) the flux concentration regime, where the waveform of the magnetic field is nearly a sine wave, with an amplitude exceeding that of the applied field by up to a factor of two. The distribution of the penetration regimes in the holes is compared with that of the magnetic flux density at the top and bottom surfaces of the sample, and is interpreted with the help of optical polarized light micrographs of these surfaces. We show that the measurement of the magnetic field inside the holes can be used as a local characterization of the bulk magnetic properties of the sample.

Properties of electrons and holes during femtosecond cooperative emission

Spectral and energetic characteristics of the cooperative recombination of high density electrons and holes in bulk GaAs are experimentally studied at room temperature. It is shown that the properties and parameters of femtosecond superradiant pulses are conditioned by the collective properties of electrons and holes. Electron-hole pairing and the formation of a short-living coherent e-h BCS state distinguish strongly the regime of cooperative emission from all radiative e-h recombination regimes, which have been observed earlier. The dependences of the energy gap (the order parameter), the Fermi energy, and the band gap of the coherent e-h BCS state on the concentration of electron-hole pairs are obtained.

Tensile strength of UD-composite laminates with multiple holes

The residual strength of glass fibre reinforced vinyl-ester laminates with multiple holes was investigated through an experimental programme. Different types of structured hole patterns and hole densities were investigated and analysed using digital image correlation strain measuring technique. Three different failure modes could be observed when the hole patterns and the hole densities were a altered. These three failure modes were used as the foundation for a simple yet effective analytical model in order to predict the residual strength of damaged composite specimens. Finally, a number of laminates with randomly distributed holes were tested experimentally. The analytical model can predict the failure mode and failure strength of the experiments with sufficiently good fidelity. © 2010 Elsevier Ltd.