Multi-Span statistical language modeling for large vocabulary speech recognition

The goal of multi-span language modeling is to integrate the various constraints, both local and global, that are present in the language. In this paper, local constraints are captured via the usual n-gram approach, while global constraints are taken into account through the use of latent semantic analysis. Anintegrative formulation is derivedfor the combination of these two paradigms, resulting in an en-tirely data-driven, multi-span framework for large vocabulary speech recognition. Because of the inherent comple-mentarity in the two types of constraints, the performance of the integrated language model compares favorably with the corresponding n-gram performance. Both perplexity and average word error rate (cid:12)gures are reported and dis-cussed.