Pseudo-Syntactic Language Modeling for Disfluent Speech Recognition
Michael Wallace McGreevy · Infoscience (Ecole Polytechnique Fédérale de Lausanne) · 2004
Language models for speech recognition are generally trained on text corpora. Since these corpora do not contain the disfluencies found in natural speech, there is a train/test mismatch when these models are applied to conversational speech. In this work we investigate a language model (LM) designed to model these disfluencies as a syntactic process. By modeling self-corrections we obtain an improvement over our baseline syntactic model. We also obtain a 30\\% relative reduction in perplexity from the best performing standard {N-gram} model when we interpolate it with our syntactically derived models.