An Input Output HMM Architecture

Maximum Likelihood from Incomplete Data Via the EM Algorithm

1977 • 46,601 citations

Learning long-term dependencies with gradient descent is difficult

1994 • 7,520 citations

Adaptive Mixtures of Local Experts

1991 • 4,228 citations

An Introduction to the Application of the Theory of Probabilistic Functions of a Markov Process to Automatic Speech Recognition

1983 • 996 citations

Inductive Inference: Theory and Methods

1983 • 911 citations

Learning and Extracting Finite State Automata with Second-Order Recurrent Neural Networks

1992 • 388 citations

Training Stochastic Model Recognition Algorithms as Networks can Lead to Maximum Mutual Information Estimation of Parameters

1989 • 367 citations

Links between Markov models and multilayer perceptrons

1990 • 333 citations

The induction of dynamical recognizers

1991 • 307 citations

Global optimization of a neural network-hidden Markov model hybrid

1992 • 204 citations

Induction of Finite-State Languages Using Second-Order Recurrent Networks

1992 • 149 citations

Induction of Multiscale Temporal Structure

1991 • 131 citations

Mixtures of Controllers for Jump Linear and Non-Linear Plants

1993 • 62 citations

Credit Assignment through Time: Alternatives to Backpropagation

1993 • 34 citations