The English alphabet is difficult to recognize automatically because many letters sound alike; e.g., BID, PIT, VIZ and F IS. When spoken over the telephone, the information needed to discriminate among several of these pairs, such as F IS, PIT, BID and VIZ, is further reduced due to the limited bandwidth of the channel Speaker-independent recognition of spelled names over the telephone is difficult due to variability caused by channel distortions, different handsets, and a variety of background noises. Finally, when dealing with a large population of speakers, dialect and foreign accents alter letter pronunciations. An R from a Boston speaker may not contain an [r]. Human classification performance on telephone speech underscores the difficulty of the problem.

We propose a paradigm for modeling speech production based on neural networks. We focus on characteristics of the musculoskeletal system. Using real physiological data - articulator movements and EMG from muscle activitya neural network learns the forward dynamics relating motor commands to muscles and the ensuing articulator behavior. After learning, simulated perturbations, were used to asses properties of the acquired model, such as natural frequency, damping, and interarticulator couplings. Finally, a cascade neural network is used to generate continuous motor commands from a sequence of discrete articulatory targets.

JANUS translates continuously spoken English and German into German, English, and Japanese. JANUS currently achieves 87% translation fidelity from English speech and 97% from German speech. We present the JANUS system along with comparative evaluations of its interchangeable processing components, with special emphasis on the connectionist modules.

The subject of this paper is the integration of multi-layered Artificial Neural Networks (ANN) with probability density functions such as Gaussian mixtures found in continuous density Hidden Markov Models (HMM). In the first part of this paper we present an ANN/HMM hybrid in which all the parameters of the the system are simultaneously optimized with respect to a single criterion. In the second part of this paper, we study the relationship between the density of the inputs of the network and the density of the outputs of the networks. A few experiments are presented to explore how to perform density estimation with ANNs. 1 INTRODUCTION This paper studies the integration of Artificial Neural Networks (ANN) with probability density functions (pdf) such as the Gaussian mixtures often used in continuous density Hidden Markov Models. The ANNs considered here are multi-layered or recurrent networks with hyperbolic tangent hidden units.

Issues relating to the estimation of hidden Markov model (HMM) local probabilities are discussed. In particular we note the isomorphism of radial basis functions (RBF) networks to tied mixture density modellingj additionally we highlight the differences between these methods arising from the different training criteria employed. We present a method in which connectionist training can be modified to resolve these differences and discuss some preliminary experiments. Finally, we discuss some outstanding problems with discriminative training.

The RBF network consists of an input layer, a hidden layer composed of Gaussian basis functions, and an output layer. Connections from the input layer to the hidden layer are fixed at unity while those from the hidden layer to the output layer are trained by minimizing the overall mean-square error between actual and desired output values. Each RBF output node has a corresponding state in a set of HMM word models which represent the words in the vocabulary. HMM word models are left-to-right with no skip states and have a one-state background noise model at either end. The background noise models are identical for all words.

Such systems attempt to combine the best features of both models: the temporal structure of HMMs and the discriminative power of neural networks. In this work we define a time-warping (1W) neuron that extends the operation of the fonnal neuron of a back-propagation network by warping the input pattern to match it optimally to its weights. We show that a single-layer network of TW neurons is equivalent to a Gaussian density HMMbased recognition system.

The focused gamma network is proposed as one of the possible implementations of the gamma neural model. The focused gamma network is compared with the focused backpropagation network and TDNN for a time series prediction problem, and with ADALINE in a system identification problem.

We present the "Multi-State Time Delay Neural Network" (MS-TDNN) as an extension of the TDNN to robust word recognition.

It seems quite natural to assume that the limited capacity is due to the special dynamical nature of STM. Recently, Crick and Koch (1990) suggested that the working memory is functionally related to the binding process, and is obtained via synchronized oscillations of neural populations. The capacity limitation of STM may then result from the competition between oscillations representing items in STM. In the model which we investigate this is indeed the case.