Expressive Probability Models For Speech Recognition And Understanding

The paper is a brief summary of an invited talk given at the ASRU 99 conference. The principal points are as follows: first, that the expressive power of the probabilitymodels available for use in speech recognition and understanding has expanded significantly; second, that using expressive models such as dynamic Bayesian networks can result in improved learning rates and recognition results; and finally that still further expansion is required to tackle many problems of interest in the area of speech understanding. This further expansion should combine probability theory with the expressive power of first-order logical languages. The paper sketches an approximate inference method for representation systems of this kind.

[1]  Neil Gordon,et al.  Bayesian methods for tracking , 1993 .

[2]  Arnaud Doucet,et al.  Sequential Monte Carlo Methods to Train Neural Network Models , 2000, Neural Computation.

[3]  Michael I. Jordan,et al.  Probabilistic Independence Networks for Hidden Markov Probability Models , 1997, Neural Computation.

[4]  Xavier Boyen,et al.  Discovering the Hidden Structure of Complex Dynamic Systems , 1999, UAI.

[5]  Uffe Kjærulff,et al.  A Computational Scheme for Reasoning in Dynamic Probabilistic Networks , 1992, UAI.

[6]  Thomas L. Dean,et al.  Probabilistic Temporal Reasoning , 1988, AAAI.

[7]  Joseph Y. Halpern.  An Analysis of First-Order Logics of Probability , 1989, IJCAI.

[8]  Stuart J. Russell,et al.  Stochastic simulation algorithms for dynamic probabilistic networks , 1995, UAI.

[9]  Hong C. Leung,et al.  PhoneBook: a phonetically-rich isolated-word telephone-speech database , 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

[10]  M. Polymeropoulos,et al.  Mapping of a Gene for Parkinson's Disease to Chromosome 4q21-q23 , 1996, Science.

[11]  Geoffrey Zweig,et al.  Probabilistic modeling with Bayesian networks for automatic speech recognition , 1998, ICSLP.

[12]  S. Muggleton.  Stochastic Logic Programs , 1996 .

[13]  Ulf Grenander,et al.  General Pattern Theory: A Mathematical Study of Regular Structures , 1993 .

[14]  Avi Pfeffer,et al.  Probabilistic Frame-Based Systems , 1998, AAAI/IAAI.

[15]  Robert P. Goldman,et al.  Probabilistic text understanding , 1992 .

[16]  Peter Green,et al.  Markov chain Monte Carlo in Practice , 1996 .

[17]  Kevin P. Murphy,et al.  Learning the Structure of Dynamic Probabilistic Networks , 1998, UAI.

[18]  Andrew H. Gee,et al.  Hybrid sequential Monte Carlo/Kalman methods to train neural networks in non-stationary environments , 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

[19]  Geoffrey Zweig,et al.  Speech Recognition with Dynamic Bayesian Networks , 1998, AAAI/IAAI.

[20]  Zoubin Ghahramani,et al.  A Unifying Review of Linear Gaussian Models , 1999, Neural Computation.

[21]  J. Felsenstein.  Inferring phylogenies from protein sequences by parsimony, distance, and likelihood methods. , 1996, Methods in enzymology.