Speech dereverberation is desirable with a view to achieving, for example, robustspeech recognition in the real world. However, it is still a challenging problem,especially when using a single microphone. Although blind equalization techniques have been exploited, they cannot deal with speech signals appropriately because their assumptions are not satisfied by speech signals. We propose a new dereverberation principle based on an inherent property of speech signals, namely quasi-periodicity. The present methods learn the dereverberation filter from a lot of speech data with no prior knowledge of the data, and can achieve high quality speech dereverberation especially when the reverberation time is long.

In recent years, there has been a lot of interest in the study of kernel methods [1].

Figure 1: In the generative model, the spectrogram is obtained by taking overlapping windows of length n from the time-domain speech signal, and computing the energy spectrum.

Over the last years significant efforts have been made to develop kernels that can be applied to sequence data such as DNA, text, speech, video and images. The Fisher Kernel and similar variants have been suggested as good ways to combine an underlying generative model in the feature space and discriminant classifiers such as SVM's. In this paper we suggest analternative procedure to the Fisher kernel for systematically finding kernel functions that naturally handle variable length sequence data in multimedia domains. In particular for domains such as speech and images we explore the use of kernel functions that take full advantage of well known probabilistic models such as Gaussian Mixtures and single fullcovariance Gaussian models. We derive a kernel distance based on the Kullback-Leibler (KL) divergence between generative models. In effect our approach combines the best of both generative and discriminative methodsand replaces the standard SVM kernels. We perform experiments on speaker identification/verification and image classification tasksand show that these new kernels have the best performance in speaker verification and mostly outperform the Fisher kernel based SVM's and the generative classifiers in speaker identification and image classification.

We consider the problem of teXt-independent speaker verification.

We will exemplify our reasoning using data from an experiment described in Sect.

A distinction in our method is the use of Volterra kernels to filter the particles, which live in a high dimensional space.

When we learn a new motor skill, we have to contend with both the variability inherentin our sensors and the task. The sensory uncertainty can be reduced by using information about the distribution of previously experienced tasks.Here we impose a distribution on a novel sensorimotor task and manipulate the variability of the sensory feedback. We show that subjects internally represent both the distribution of the task as well as their sensory uncertainty. Moreover, they combine these two sources of information in a way that is qualitatively predicted by optimal Bayesian processing. We further analyze if the subjects can represent multimodal distributions such as mixtures of Gaussians. The results show that the CNS employs probabilistic models during sensorimotor learning even when the priors are multimodal.

These experimentally-determined rules (usually called spike-time dependent plasticity or STDP rules), which are constantly being refined,18,3o have inspired substantialfurther theoretical work on their modeling and interpretation.2·9,l0,22·28·29·33 Figurel(Dl-Gl)* depict some of the main STDP findings/ of which the best-investigated are shown in figure l(Dl;El), and are variants of a'standard' STDP rule. Earlier work considered rate-based rather than spikebased temporalrules, and so we adopt the broader term'time dependent plasticity' or TDP. Note the strong temporal asymmetry in both the standard rules. Although the theoretical studies have provided us with excellent tools for modeling thedetailed consequences of different time-dependent rules, and understanding characteristicssuch as long-run stability and the relationship with non-temporal learning rules such as BCM,6 specifically computational ideas about TDP are rather thinner on the ground. Two main qualitative notions explored in various of the works cited above are that the temporal asymmetries inTDP rules are associated with causality or prediction. However, looking specifically at the standard STDP rules, models interested in prediction *We refer to graphs in this figure by row and column.

The connectivity of the nervous system of the nematode Caenorhabditis eleganshas been described completely, but the analysis of the neuronal basisof behavior in this system is just beginning. Here, we used an optimization algorithm to search for patterns of connectivity sufficient tocompute the sensorimotor transformation underlying C. elegans chemotaxis, a simple form of spatial orientation behavior in which turning probabilityis modulated by the rate of change of chemical concentration.