Continuous Speech Recognition Using Hidden Markov Models

Stochastic signal processing techniques have pro-foundly changed our perspective on speech processing. We have witnessed a progression from heuristic algo-rithms to detailed statistical approaches based on itera-t ive analysis techniques. Markov modeling provides a mathematically rigorous approach to developing robust s tat is t ica l signal models. Since t h e i n t roduc t i on of Markov models t o speech processing in t h e middle 1970s. continuous speech recognition technology has come of age. Dramatic advances have been made in characterizing the temporal and spectral evolution of the speech signal. A t the same time, our appreciation o f t he need to explain complex acoustic manifestations b y integration of application constraints in to low level signal processing has grown. In th is paper, w e review the use of Markov models in continuous speech recogni-tion. Markov models are presented as a generalization of i t s predecessor technology, Dynamic Programming. A unified view is offered in which bo th linguistic decoding and acoustic matching are integrated in to a single opti-mal network search framework