A novel multisensory device for the assessment and rehabilitation of perceptual and attentional competencies.

The present study aims to assess a novel technological device suitable for investigating perceptual and attentional competencies in people with or without sensory impairment. The TechPAD is a cabled system including embedded sensors and actuators to enable visual, auditory, and tactile interactions and a capacitive surface receiving inputs from the user. The system is conceived to create multisensory environments, using multiple units controlled separately and simultaneously. We assessed the device by adapting a spatial attention task comparing performances in different cognitive load conditions (high or low) and stimulation (unimodal, bimodal, or trimodal). 28 sighted adults were asked to monitor both the central and peripheral parts of the device and to tap a target stimulus (either visual, auditory, haptic, or multimodal) as fast as they could. Our results suggest that this new device can provide congruent and incongruent multimodal stimuli and quantitatively measure parameters such as reaction time and accuracy, allowing to investigate perceptual mechanisms in multisensory environments.Clinical Relevance-The TechPad is a reliable tool for the assessment of spatial attention during interactive tasks. its application in clinical trials will pave the way to its role in multisensory rehabilitation.

A hybrid random field model for scalable statistical learning.

This paper introduces hybrid random fields, which are a class of probabilistic graphical models aimed at allowing for efficient structure learning in high-dimensional domains. Hybrid random fields, along with the learning algorithm we develop for them, are especially useful as a pseudo-likelihood estimation technique (rather than a technique for estimating strict joint probability distributions). In order to assess the generality of the proposed model, we prove that the class of pseudo-likelihood distributions representable by hybrid random fields strictly includes the class of joint probability distributions representable by Bayesian networks. Once we establish this result, we develop a scalable algorithm for learning the structure of hybrid random fields, which we call 'Markov Blanket Merging'. On the one hand, we characterize some complexity properties of Markov Blanket Merging both from a theoretical and from the experimental point of view, using a series of synthetic benchmarks. On the other hand, we evaluate the accuracy of hybrid random fields (as learned via Markov Blanket Merging) by comparing them to various alternative statistical models in a number of pattern classification and link-prediction applications. As the results show, learning hybrid random fields by the Markov Blanket Merging algorithm not only reduces significantly the computational cost of structure learning with respect to several considered alternatives, but it also leads to models that are highly accurate as compared to the alternative ones.

Robust combination of neural networks and hidden Markov models for speech recognition.

Acoustic modeling in state-of-the-art speech recognition systems usually relies on hidden Markov models (HMMs) with Gaussian emission densities. HMMs suffer from intrinsic limitations, mainly due to their arbitrary parametric assumption. Artificial neural networks (ANNs) appear to be a promising alternative in this respect, but they historically failed as a general solution to the acoustic modeling problem. This paper introduces algorithms based on a gradient-ascent technique for global training of a hybrid ANN/HMM system, in which the ANN is trained for estimating the emission probabilities of the states of the HMM. The approach is related to the major hybrid systems proposed by Bourlard and Morgan and by Bengio, with the aim of combining their benefits within a unified framework and to overcome their limitations. Several viable solutions to the "divergence problem"-that may arise when training is accomplished over the maximum-likelihood (ML) criterion-are proposed. Experimental results in speaker-independent, continuous speech recognition over Italian digit-strings validate the novel hybrid framework, allowing for improved recognition performance over HMMs with mixtures of Gaussian components, as well as over Bourlard and Morgan's paradigm. In particular, it is shown that the maximum a posteriori (MAP) version of the algorithm yields a 46.34% relative word error rate reduction with respect to standard HMMs.