Showing papers by "Richard P. Lippmann published in 1988"

An introduction to computing with neural nets

Abstract: Artificial neural net models have been studied for many years in the hope of achieving human-like performance in the fields of speech and image recognition. These models are composed of many nonlinear computational elements operating in parallel and arranged in patterns reminiscent of biological neural nets. Computational elements or nodes are connected via weights that are typically adapted during use to improve performance. There has been a recent resurgence in the field of artificial neural nets caused by new net topologies and algorithms, analog VLSI implementation techniques, and the belief that massive parallelism is essential for high performance speech and image recognition. This paper provides an introduction to the field of artificial neural nets by reviewing six important neural net models that can be used for pattern classification. These nets are highly parallel building blocks that illustrate neural net components and design principles and can be used to construct more complex systems. In addition to describing these nets, a major emphasis is placed on exploring how some existing classification and clustering algorithms can be performed using simple neuron-like components. Single-layer nets can implement algorithms required by Gaussian maximum-likelihood classifiers and optimum minimum-error classifiers for binary patterns corrupted by noise. More generally, the decision regions required by any classification algorithm can be generated in a straightforward manner by three-layer feed-forward nets.

Neutral nets for computing

Abstract: There has been a resurgence of interest in neutral net models composed of many simple interconnected processing elements operating in parallel. The computational power of different neutral net models and the effectiveness of simple error correction training procedures have been demonstrated. Three important feed-forward models are described. Single- and multi-layer perceptrons which can be used for pattern classification are described, as well as Kohonen's feature map algorithm which can be used for clustering or as a vector quantizer. A major emphasis is placed on relating these models to existing classification and clustering algorithms. >

A neural net approach to speech recognition

Abstract: Artificial neural networks are of interest because algorithms used in many speech recognizers can be implemented using highly parallel neural net architectures and because new parallel algorithms are being development that are inspired by biological nervous systems. Some neural net approaches are resented for the problem of static pattern classification and time alignment. For static pattern classification, multi-layer perceptron classifiers trained with back propagation can form arbitrary decision regions, are robust, and train rapidly for convex decision regions. For time alignment, the Viterbi net is a neural net implementation of the Viterbi decoder used very effectively in recognition systems based on hidden Markov models (HMMs). >

Adaptive Neural Net Preprocessing for Signal Detection in Non-Gaussian Noise

Abstract: A nonlinearity is required before matched filtering in minimum error receivers when additive noise is present which is impulsive and highly non-Gaussian. Experiments were performed to determine whether the correct clipping nonlinearity could be provided by a single-input single-output multi-layer perceptron trained with back propagation. It was found that a multi-layer perceptron with one input and output node, 20 nodes in the first hidden layer, and 5 nodes in the second hidden layer could be trained to provide a clipping nonlinearity with fewer than 5,000 presentations of noiseless and corrupted waveform samples. A network trained at a relatively high signal-to-noise (S/N) ratio and then used as a front end for a linear matched filter detector greatly reduced the probability of error. The clipping nonlinearity formed by this network was similar to that used in current receivers designed for impulsive noise and provided similar substantial improvements in performance.

Dynamic adaptation of Hidden Markov models for robust isolated-word speech recognition

Abstract: The authors describe an HMM-based isolated-word recognition system that dynamically adapts word model parameters to new speakers and to stress-induced speech variations. During recognition all input tokens presented to the system can be used to augment the current word model parameters. New tokens can be weighted so that adaptation simply increases the size of the training set, or tracks systematic changes by exponentially weighting all previously seen data. This system was tested on the 35-word 10710 token Lincoln stressed speech data base. Speaker adaptation experiments produced error rates equivalent to speaker-trained systems after the presentation of only a single new token per vocabulary word. Stress condition adaptation experiments produced results comparable to multistyle-trained systems after the presentation of several new tokens per vocabulary word. >

S1.7 A Neural Network for Isolated-Word Recognition1

Abstract: Algorithms that are implementable by artificial neural networks show promise of augmenting the field of automatic speech recognition. A specific approach to the problem of isolated-word recognition was initiated by Tank and Hopfield [5]. Recently, these ideas were applied to a concatenated system consisting of a vector quantizer, a time concentrator with vector sequences as input and allophones as output and a final stage with allophone sequence as input and isolated words as output [GI. Recent improvements in the system will be discussed; included are the addition of data-dependent “phonological” rules that yielded improved results for a single-speaker 35-word vocabulary isolatedword recognition task.

Neural nets for speech recognition

Abstract: Artificial neural networks are of interest for two main reasons. First, they provide architectures to implement many algorithms used in speech rccognizcrs with fine grain massive parallelism. Second, they are leading to new computational algorithms and new approaches to speech recognition inspired by biological nervous systems. Neural net approaches to the problems of speech preprocessing, pattern classification, and time alignment are reviewed. Preprocessors using auditory nerve time‐synchrony models have provided improved recognition performance in noise [O. Ghitza, ICASSP 87, 2372–2375]. Highly parallel neural net architectures exist to implement many important traditional classification algorithms, such as k‐nearest neighbor and Gaussian classifiers [R. Lippmann, IEEE ASSP Mag. 4(2), 4–22 (1987)]. Newer multilayer perceptron classifiers trained with back propagation can form arbitrary decision regions, are robust, and train rapidly for convex decision regions. These nets performed as well as conventio...