Index-based incremental language model for scalable directory assistance

As the ubiquitous access to vast and remote information sources from portable devices becomes commonplace, the need from users to perform searches in keyboard-unfriendly situations grows substantially, thus triggering the increased demand of voice search sessions. This paper proposes a methodology that addresses different dimensions of scalability of mixed-initiative voice search in automatic spoken dialog systems.The strategy is based on splitting the complexity of the fully-constrained grammar (one that tightly covers the entire hypothesis space) into a fixed/low complexity phonotactic grammar followed by an index mechanism that dynamically assembles a second-pass grammar that consists of only a handful of hypotheses. The experimental analysis demonstrates different dimensions of scalability achieved by the proposed method using actual Whitepages-residential data.

► We study different facets of scalability in mixed-initiative directory assistance.
► A phone recognizer and an index mechanism are combined to keep the complexity low.
► Our method achieves high performance while preserving scalability properties.
► The implemented pruning strategies were effective in keeping memory usage low.