Abstract

vi Abbreviations vii Notation viii 1 Introduction 1 2 Hidden Markov Models 4 2.1 Definition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.2 HMM Modelling Assumptions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.3 HMM Topology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.4 Finding the Best Transcription . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 2.5 Setting the Parameters . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10 2.6 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 3 Objective Functions 19 3.1 Properties of Maximum Likelihood Estimators . . . . . . . . . . . . . . . . . . . 19 3.2 Maximum Likelihood . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 3.3 Maximum Mutual Information . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25 3.4 Frame Discrimination . . . . . . . . . . . . . . . . ....

Citations

6232	Maximum likelihood from incomplete data via the em algorithm - Dempster, Laird, et al. - 1977
573	A maximization technique occurring in the statistical analysis of probabilistic functions of Markov chains - Baum, Petrie, et al. - 1970
537	Neural networks and the bias/variance dilemma - Geman, Bienenstock, et al. - 1992
422	An Inequality and Associated Maximization Technique in Statistical Estimation of a Markov Process - Baum - 1972
286	Interpolated estimation of Markov source parameters from sparse data - Jelinek, Mercer - 1980
233	Neural Network Classifiers Estimate Bayesian a posteriori Probabilities - Richard, Lippmann - 1991
205	An Empirical Study of Learning Speed in Back-Propagation Networks - Fahlman - 1988
187	Speakerindependent phone recognition using hidden Markov models - Lee, Hon - 1989
159	The effective number of parameters: an analysis of generalization and regularization in nonlinear learning systems”, in eds - Moody - 1992
121	Mathematical statistics - Wilks - 1962
108	Second-Order Methods for Learning: Between Steepest Descent and Newton's Method - Battiti, First- - 1992
94	A theory of adaptive pattern classifiers - Amari - 1967
88	Links between Markov Models and Multilayer Perceptrons - Bourlard, Wellekens - 1989
79	Maximum likelihood estimation for multivariate observations of Markov sources - Liporace - 1982
77	An inequality for rational functions with applications to some statistical estimation problems - Gopalakrishnan, Kanevsky, et al. - 1991
50	Equivalence Proofs for Multi-Layer Perceptron Classifiers and the Bayesian Discriminant Function - Hampshire, Pearlmutter - 1991
49	Continuous Speech Recognition using Multilayer Perceptrons with Hidden Markov Models - Morgan, Bourlard
47	A Novel Objective Function for Improved Phoneme Recognition Using Time-Delay Neural Networks - Hampshire, Waibel - 1990
45	Utans J: Principled Architecture Selection for Neural Networks: Application to Corporate Bond Rating Prediction - Moody
45	Connectionists probability estimators in HMM speech recognition - Renals, Morgan, et al. - 1994
44	A probabilistic approach to the understanding and training ofneural network classifiers - GISH - 1990
41	Vector quantization for the efficient computation of continuous density likelihoods - Bocchieri - 1993
37	Context-Dependent Classes in a Hybrid Recurrent Network-HMM Speech Recognition System - Kershaw, Hochberg, et al. - 1996
36	An improved mmie training algorithm for speaker-independent, small vocabulary, continuous speech recognition - Normandin, Morgera - 1991
35	Neural Networks for Statistical Recognition of Continuous Speech - Morgan, Bourlard - 1995
34	High-performance connected digit recognition using maximum mutual information estimation,” Speech and Audio Processing - Normandin, Cardin, et al. - 1994
33	MMI Training for Continuous Phoneme Recognition on the TIMIT Database - Kapadia, Valtchev, et al. - 1993
29	The ISOLET Spoken Letter Database - Cole, Muthusamy, et al. - 1990
28	J: Selecting neural network architectures via the prediction risk application to corporate bond rating prediction - Utans, Moody - 1991
27	Optimization for training neural nets - Barnard - 1992
21	The Bucket Box Intersection (BBI) Algorithm for Fast Approximative Evaluation of Diagonal Mixture Gaussians - Fritsch, Rogina - 1996
21	Voice and Speech Processing - PARSONS - 1987
20	Minimum error rate training of inter-word context dependent acoustic model units in speech recognition - Chou, Lee, et al. - 1994
19	A generalization of the Baum algorithm to rational objective functions - Gopalakrishnan, Kanevsky, et al. - 1989
18	R.,1990, Estimation of Hidden Markov Model Parameters By Minimizing Empirical Error Rate - Ljolje, Ephraim, et al.
18	Phoneme recognition from the timit database using recurrent error propagation networks - Robinson, Fallside - 1990
18	IPA: Improved phone modelling with recurrent neural networks - Robinson, Hochberg, et al. - 1994
17	MMIE training for large vocabulary continuous speech recognition - Normandin, Lacouture, et al. - 1994
16	An inequality with applications to statistical prediction for functions of Markov processes and to a model of ecology - Baum, Eagon - 1967
16	Optimization schemes for neural networks - Jervis, Fitzgerald - 1993
16	Algorithms for an optimal a* search and linearizing the search in the stack decoder - Paul - 1991
14	A Hybrid Speech Recognition System using HMMS with an LVQ-Trained Codebook, ICASSP - Iwamida, Katagiri, et al. - 1990
12	Markov Models, Maximum Mutual Information Estimation, and the Speech Recognition Problem - Hidden - 1991
11	A differential theory of learning for efficient statistical pattern recognition - Hampshire - 1993
9	Inter-Word Coarticulation Modeling and MMIE Training for Improved Connected Digit Recognition - Cardin, Normandin, et al. - 1993
9	Speaker-independent large vocabulary word recognition using an LVQ/HMM hybrid algorithm - Iwamida, Katagiri, et al. - 1991
9	Optimising hidden markov models using discriminative output distributions - Woodland, Cole - 1991
8	Remarks on the measurement of subjective probability and information - Aczel, Pfanzagl - 1966
7	Performance and generalization of the classification figure of merit criterion function - Barnard - 1991
7	Probability estimation by feed-forward networks in continuous speech recognition - Renals, Morgan, et al. - 1991