Variational approximations are becoming a widespread tool for Bayesian learning of graphical models. We provide some theoretical results for the variational updates in a very general family of conjugate-exponential graphical models. We show how the belief propagation and the junction tree algorithms can be used in the inference step of variational Bayesian learning. Applying these results to the Bayesian analysis of linear-Gaussian state-space models we obtain a learning procedure that exploits the Kalman smoothing propagation, while integrating over all model parameters. We demonstrate how this can be used to infer the hidden state dimensionality of the state-space model in a variety of synthetic problems and one real high-dimensional data set. 1 Introduction Bayesian approaches to machine learning have several desirable properties.

So which of the two variances is "correct"? From a modelling point of view, the variance from the test example tells us the true story, so the training set variance should be regarded as biased.

Two avenues will be explored: the first is to maximize the ()-average divergence between the class densities and the second is to minimize the union Bhattacharyya bound in the range of (). While both approaches yield similar performance in practice, they outperform standard LDA features and show a 10% relative improvement in the word error rate over state-of-the-art cepstral features on a large vocabulary telephony speech recognition task. 1 Introduction Modern speech recognition systems use cepstral features characterizing the short-term spectrum of the speech signal for classifying frames into phonetic classes. These features are augmented with dynamic information from the adjacent frames to capture transient spectral events in the signal.

In memory consolidation, declarative memories which initially require the hippocampus for their recall, ultimately become independent of it. Consolidation has been the focus of numerous experimental and qualitative modeling studies, but only little quantitative exploration. We present a consolidation model in which hierarchical connections in the cortex, that initially instantiate purely semantic information acquired through probabilistic unsupervised learning, come to instantiate episodic information as well. The hippocampus is responsible for helping complete partial input patterns before consolidation is complete, while also training the cortex to perform appropriate completion by itself.

Stimulus arrays are inevitably presented at different positions on the retina in visual tasks, even those that nominally require fixation. In particular, this applies to many perceptual learning tasks. We show that perceptual inference or discrimination in the face of positional variance has a structurally different quality from inference about fixed position stimuli, involving a particular, quadratic, non-linearity rather than a purely linear discrimination. We show the advantage taking this non-linearity into account has for discrimination, and suggest it as a role for recurrent connections in area VI, by demonstrating the superior discrimination performance of a recurrent network. We propose that learning the feedforward and recurrent neural connections for these tasks corresponds to the fast and slow components of learning observed in perceptual learning tasks. 1 Introduction The field of perceptual learning in simple, but high precision, visual tasks (such as vernier acuity tasks) has produced many surprising results whose import for models has yet to be fully felt.

For SNR-estimation, the input signal is transformed into so-called Amplitude Modulation Spectrograms (AMS), which represent both spectral and temporal characteristics of the respective analysis frame, and which imitate the representation of modulation frequencies in higher stages of the mammalian auditory system. A neural network is used to analyse AMS patterns generated from noisy speech and estimates the local SNR. Noise suppression is achieved by attenuating frequency channels according to their SNR. The noise suppression algorithm is evaluated in speakerindependent digit recognition experiments and compared to noise suppression by Spectral Subtraction. 1 Introduction One of the major problems in automatic speech recognition (ASR) systems is their lack of robustness in noise, which severely degrades their usefulness in many practical applications. Several proposals have been made to increase the robustness of ASR systems, e.g. by model compensation or more noise-robust feature extraction [1, 2]. Another method to increase robustness of ASR systems is to suppress the background noise before feature extraction. Classical approaches for single-channel noise suppression are Spectral Subtraction [3] and related schemes, e.g.

Two well known classes of unsupervised procedures that can be cast in this manner are generative and recoding models. In a generative unsupervised framework, the environment generates training exampleswhich we will refer to as observations-by sampling from one distribution; the other distribution is embodied in the model. Examples of generative frameworks are mixtures of Gaussians (MoG) [2], factor analysis [4], and Boltzmann machines [8]. In the recoding unsupervised framework, the model transforms points from an obser- vation space to an output space, and the output distribution is compared either to a reference distribution or to a distribution derived from the output distribution. An example is independent component analysis (leA) [11], a method that discovers a representation of vector-valued observations in which the statistical dependence among the vector elements in the output space is minimized.

The naive mean-field approach fails in this case whereas linear response theory-which gives an improved estimate of covariances-is very efficient. The examples given are for sources without temporal correlations .

Using statistical mechanics results, I calculate learning curves (average generalization error) for Gaussian processes (GPs) and Bayesian neural networks (NNs) used for regression. Applying the results to learning a teacher defined by a two-layer network, I can directly compare GP and Bayesian NN learning.

In this paper, we discuss some new research directions in automatic speech recognition (ASR), and which somewhat deviate from the usual approaches. More specifically, we will motivate and briefly describe new approaches based on multi-stream and multi/band ASR. These approaches extend the standard hidden Markov model (HMM) based approach by assuming that the different (frequency) channels representing the speech signal are processed by different (independent) "experts", each expert focusing on a different characteristic of the signal, and that the different stream likelihoods (or posteriors) are combined at some (temporal) stage to yield a global recognition output. As a further extension to multi-stream ASR, we will finally introduce a new approach, referred to as HMM2, where the HMM emission probabilities are estimated via state specific feature based HMMs responsible for merging the stream information and modeling their possible correlation.