We present a sequential Monte Carlo method applied to additive noise compensation for robust speech recognition in time-varying noise. The method generates a set of samples according to the prior distribution given by clean speech models and noise prior evolved from previous estimation. An explicit model representing noise ef- fects on speech features is used, so that an extended Kalman filter is constructed for each sample, generating the updated continuous state estimate as the estimation of the noise parameter, and predic- tion likelihood for weighting each sample. Minimum mean square error (MMSE) inference of the time-varying noise parameter is car- ried out over these samples by fusion the estimation of samples ac- cording to their weights. A residual resampling selection step and a Metropolis-Hastings smoothing step are used to improve calcula- tion e#ciency. Experiments were conducted on speech recognition in simulated non-stationary noises, where noise power changed ar- tificially, and highly non-stationary Machinegun noise.

The hierarchical hidden Markov model (HHMM) is a generalization of the hidden Markov model (HMM) that models sequences with structure at many length/time scales [FST98]. Unfortunately, the original infer- is ence algorithm is rather complicated, and takes the length of the sequence, making it impractical for many domains. In this paper, we show how HHMMs are a special kind of dynamic Bayesian network (DBN), and thereby derive a much simpler inference algorithm, which only takes time. Furthermore, by drawing the connection between HHMMs and DBNs, we enable the application of many stan- dard approximation techniques to further speed up inference.

A new class of Support Vector Machine (SVM) that is applica- ble to sequential-pattern recognition such as speech recognition is developed by incorporating an idea of non-linear time alignment into the kernel function. Since the time-alignment operation of sequential pattern is embedded in the new kernel function, stan- dard SVM training and classification algorithms can be employed without further modifications. The proposed SVM (DTAK-SVM) is evaluated in speaker-dependent speech recognition experiments of hand-segmented phoneme recognition. Preliminary experimen- tal results show comparable recognition performance with hidden Markov models (HMMs). 1 Introduction Support Vector Machine (SVM) [1] is one of the latest and most successful statistical pattern classifier that utilizes a kernel technique [2, 3].

Logistic units in the first hidden layer of a feedforward neural net(cid:173) work compute the relative probability of a data point under two Gaussians. This leads us to consider substituting other density models. We present an architecture for performing discriminative learning of Hidden Markov Models using a network of many small HMM's. Experiments on speech data show it to be superior to the standard method of discriminatively training HMM's.

In previous work on transformed mixtures of Gaussians'' andtransformed hidden Markov models'', we showed how the EM al- gorithm in a discrete latent variable model can be used to jointly normalize data (e.g., center images, pitch-normalize spectrograms) and learn a mixture model of the normalized data. The only input to the algorithm is the data, a list of possible transformations, and the number of clusters to find. The main criticism of this work was that the exhaustive computation of the posterior probabili- ties over transformations would make scaling up to large feature vectors and large sets of transformations intractable. Here, we de- scribe how a tremendous speed-up is acheived through the use of a variational technique for decoupling transformations, and a fast Fourier transform method for computing posterior probabilities. We give results on learning a 4-component mixture model from a video sequence with frames of size 320240.

In the missing data' approach to improving the robustness of automatic speech recognition to added noise, an initial process identifies spectral- temporal regions which are dominated by the speech source. The remaining regions are considered to bemissing'. In this paper we develop a connectionist approach to the problem of adapting speech recognition to the missing data case, using Recurrent Neural Networks. In contrast to methods based on Hidden Markov Models, RNNs allow us to make use of long-term time constraints and to make the problems of classification with incomplete data and imputing missing values interact. We report encouraging results on an isolated digit recognition task. 1. Introduction Automatic Speech Recognition systems perform reasonably well in controlled and matched training and recognition conditions.

Acetylcholine (ACh) has been implicated in a wide variety of tasks involving attentional processes and plasticity. Following extensive animal studies, it has previously been suggested that ACh reports on uncertainty and controls hippocampal, cortical and cortico-amygdalar plasticity. We extend this view and consider its effects on cortical representational inference, arguing that ACh controls the balance between bottom-up inference, in(cid:3)uenced by input stimuli, and top-down inference, in(cid:3)uenced by contextual information. We illustrate our proposal using a hierarchical hid- den Markov model.

In reinforcement learning problems, the aim is to select a controller that will maximize the average reward in some environment.

We describe a computer system that provides a real-time musi(cid:173) cal accompaniment for a live soloist in a piece of non-improvised music for soloist and accompaniment. A Bayesian network is devel(cid:173) oped that represents the joint distribution on the times at which the solo and accompaniment notes are played, relating the two parts through a layer of hidden variables. The network is first con(cid:173) structed using the rhythmic information contained in the musical score. The network is then trained to capture the musical interpre(cid:173) tations of the soloist and accompanist in an off-line rehearsal phase. During live accompaniment the learned distribution of the network is combined with a real-time analysis of the soloist's acoustic sig(cid:173) nal, performed with a hidden Markov model, to generate a musi(cid:173) cally principled accompaniment that respects all available sources of knowledge.

We show that states of a dynamical system can be usefully repre(cid:173) sented by multi-step, action-conditional predictions of future ob(cid:173) servations. State representations that are grounded in data in this way may be easier to learn, generalize better, and be less depen(cid:173) dent on accurate prior models than, for example, POMDP state representations. Building on prior work by Jaeger and by Rivest and Schapire, in this paper we compare and contrast a linear spe(cid:173) cialization of the predictive approach with the state representa(cid:173) tions used in POMDPs and in k-order Markov models. Ours is the first specific formulation of the predictive idea that includes both stochasticity and actions (controls). We show that any system has a linear predictive state representation with number of predictions no greater than the number of states in its minimal POMDP model.