On Reduction via Determinization of Speech-Recognition Lattices

We establish a framework for studying the behavior of automatic speech recognition (ASR) lattices (viewed as automata) undergoing determinization. Using this framework, we provide initial insights into what causes determinization to produce smaller (or bigger) lattices when used in the ASR application. Our results counter the prevailing wisdom that the graph topology underlying an automaton, not the weights on the arcs, governs deterministic expansion. We show that there are graphs that expand solely due to their weights when determinized; i.e., we demonstrate graphs that expand under some weightings yet contract under others. Furthermore, we give evidence that the automata that arise in ASR are either the kind that never expand or else the weight-dependent kind; i.e., we do not nd in ASR any instances of automata that always expand under determinization. Therefore, understanding what causes weight dependence becomes essential to providing tools to avoid deterministic expansion in ASR, and we provide some theoretical results that start to explain this behavior.