Bayesian adaptation and adaptively trained systems

As the use of found data increases, more systems are being built using adaptive training. Here transforms are used to represent unwanted acoustic variability, e.g. speaker and acoustic environment changes, allowing a canonical model that models only the "pure" variability of speech to be trained. Adaptive training may be described within a Bayesian framework. By using complexity control approaches to ensure robust parameter estimates, the standard point estimate adaptive training can be justified within this Bayesian framework. However during recognition there is usually no control over the amount of data available. It is therefore preferable to be able to use a full Bayesian approach to applying transforms during recognition rather than the standard point estimates. This paper discusses various approximations to Bayesian approaches including a new variational Bayes approximation. The application of these approaches to state-of-the-art adaptively trained systems using both CAT and MLLR transforms is then described and evaluated on a large vocabulary speech recognition task. © 2005 IEEE.

How is somatosensory information used to adapt to changes in the mechanical environment?

Recent studies examining adaptation to unexpected changes in the mechanical environment highlight the use of position error in the adaptation process. However, force information is also available. In this chapter, we examine adaptation processes in three separate studies where the mechanical environment was changed intermittently. We compare the expected consequences of using position error and force information in the changes to motor commands following a change in the mechanical environment. In general, our results support the use of position error over force information and are consistent with current computational models of motor learning. However, in situations where the change in the mechanical environment eliminates position error the central nervous system does not necessarily respond as would be predicted by these models. We suggest that it is necessary to take into account the statistics of prior experience to account for our observations. Another deficiency in these models is the absence of a mechanism for modulating limb mechanical impedance during adaptation. We propose a relatively simple computational model based on reflex responses to perturbations which is capable of accounting for iterative changes in temporal patterns of muscle co-activation.

Augmenting depth camera output using photometric stereo

We present a system for augmenting depth camera output using multispectral photometric stereo. The technique is demonstrated using a Kinect sensor and is able to produce geometry independently for each frame. Improved reconstruction is demonstrated using the Kinect's inbuilt RGB camera and further improvements are achieved by introducing an additional high resolution camera. As well as qualitative improvements in reconstruction a quantitative reduction in temporal noise is shown. As part of the system an approach is presented for relaxing the assumption of multispectral photometric stereo that scenes are of constant chromaticity to the assumption that scenes contain multiple piecewise constant chromaticities.

Intragranular and intergranular behaviour of multifilamentary Bi-2223/Ag tapes

This communication aims at reporting the superconducting properties of Bi-2223/Ag tapes determined by using various measuring techniques. First, the original samples have been characterized by electrical resistance, AC susceptibility, and DC magnetization. The transport (intergranular) critical current vs. magnetic field was also determined at T = 77 K using pulsed currents up to 40 A. Next, the same combination of experiments was performed on bent tapes in order to bring out relevant information concerning the strength of the intergranular coupling. The results show that intergranular and intragranular currents differ by at least one order of magnitude. Finally, additional magnetic measurements were carried out in order to determine the anisotropy ratio Jc ab/Jc c, which was found to lie around 30. © 2002 Elsevier Science B.V. All rights reserved.

YBa2Cu3O7 tapes prepared by sol-gel deposition techniques: Microstructure and structural characterizations

We report on the preparation conditions of YBa2Cu3O7 polycrystalline superconducting tapes by a sol-gel deposition technique. We present some discussion on the compatibility between the nature of the substrate, the use of a buffer layer, and the conditions used to prepare appropriate superconducting YBa2Cu3O7 materials. We report also on the microstructural characterizations performed in order to evaluate the crystallites size, degree of orientation and connectivity. © 2002 Elsevier Science B.V. All rights reserved.