The Meta-Pi Network: Building Distributed Knowledge Representations for Robust Multisource Pattern Recognition

The authors present the Meta-Pi network, a multinetwork connectionist classifier that forms distributed low-level knowledge representations for robust pattern recognition, given random feature vectors generated by multiple statistically distinct sources. They illustrate how the Meta-Pi paradigm implements an adaptive Bayesian maximum a posteriori classifier. They also demonstrate its performance in the context of multispeaker phoneme recognition in which the Meta-Pi superstructure combines speaker-dependent time-delay neural network (TDNN) modules to perform multispeaker /b,d,g/ phoneme recognition with speaker-dependent error rates of 2%. Finally, the authors apply the Meta-Pi architecture to a limited source-independent recognition task, illustrating its discrimination of a novel source. They demonstrate that it can adapt to the novel source (speaker), given five adaptation examples of each of the three phonemes. >

[1]  W. H. Highleyman,et al.  The design and analysis of pattern recognition experiments , 1962 .

[2]  V. Hasselblad.  Estimation of parameters for a mixture of normal distributions , 1966 .

[3]  R. Redner,et al.  Mixture densities, maximum likelihood, and the EM algorithm , 1984 .

[4]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[5]  Richard M. Stern,et al.  Dynamic speaker adaptation for feature-based isolated word recognition , 1987, IEEE Trans. Acoust. Speech Signal Process..

[6]  Douglas D. O'Shaughnessy,et al.  Speech communication : human and machine , 1987 .

[7]  Dean A. Pomerleau,et al.  The meta-generalized delta rule : a new algorithm for learning in connectionist networks , 1987 .

[8]  D. F. Specht,et al.  Probabilistic neural networks for classification, mapping, or associative memory , 1988, IEEE 1988 International Conference on Neural Networks.

[9]  Victor Zue,et al.  Applications of Error Back-Propagation to Phonetic Classification , 1988, NIPS.

[10]  D. S. Touretzky,et al.  Neural network simulation at Warp speed: how we got 17 million connections per second , 1988, IEEE 1988 International Conference on Neural Networks.

[11]  Raj Reddy,et al.  Large-vocabulary speaker-independent continuous speech recognition: the sphinx system , 1988 .

[12]  Luc Devroye,et al.  Automatic Pattern Recognition: A Study of the Probability of Error , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[13]  D. F. Specht,et al.  The use of probabilistic neural networks to improve solution times for hull-to-emitter correlation problems , 1989, International 1989 Joint Conference on Neural Networks.

[14]  R. Lippmann.  Pattern classification using neural networks , 1989, IEEE Communications Magazine.

[15]  Kiyohiro Shikano,et al.  Modularity and scaling in large phonemic neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[16]  Halbert White,et al.  Learning in Artificial Neural Networks: A Statistical Perspective , 1989, Neural Computation.

[17]  Alexander H. Waibel,et al.  A novel objective function for improved phoneme recognition using time delay neural networks , 1990, International 1989 Joint Conference on Neural Networks.

[18]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[19]  B. R. Kammerer,et al.  Design of hierarchical perceptron structures and their application to the task of isolated-word recognition , 1989, International 1989 Joint Conference on Neural Networks.

[20]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[21]  Matsuoka,et al.  Syllable recognition using integrated neural networks , 1989 .

[22]  Raymond L. Watrous.  Context‐modulated discrimination of similar vowels using second‐order connectionist networks , 1989 .

[23]  Kevin J. Lang.  A time delay neural network architecture for speech recognition , 1989 .

[24]  Geoffrey E. Hinton.  20 – CONNECTIONIST LEARNING PROCEDURES1 , 1990 .

[25]  H. Gish,et al.  A probabilistic approach to the understanding and training of neural network classifiers , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[26]  Eric A. Wan,et al.  Neural network classification: a Bayesian interpretation , 1990, IEEE Trans. Neural Networks.

[27]  Hsiao-Wuen Hon,et al.  An overview of the SPHINX speech recognition system , 1990, IEEE Trans. Acoust. Speech Signal Process..

[28]  Bruce W. Suter,et al.  The multilayer perceptron as an approximation to a Bayes optimal discriminant function , 1990, IEEE Trans. Neural Networks.

[29]  H. Bourlard,et al.  Links Between Markov Models and Multilayer Perceptrons , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[30]  Xuedong Huang,et al.  On semi-continuous hidden Markov modeling , 1990, International Conference on Acoustics, Speech, and Signal Processing.

[31]  Patrick A. Shoemaker,et al.  A note on least-squares learning procedures and classification by neural network models , 1991, IEEE Trans. Neural Networks.

[32]  Eric A. Wan.  Temporal Backpropagation: An Efficient Algorithm for Finite Impulse Response Neural Networks , 1991 .

[33]  Steven J. Nowlan,et al.  Soft competitive adaptation: neural network learning algorithms based on fitting statistical mixtures , 1991 .

[34]  Michael I. Jordan,et al.  Task Decomposition Through Competition in a Modular Connectionist Architecture: The What and Where Vision Tasks , 1990, Cogn. Sci..

[35]  Geoffrey E. Hinton,et al.  Adaptive Mixtures of Local Experts , 1991, Neural Computation.