Parse structure and segmentation for improving speech recognition

Separate avenues of prior work have shown that parsing language models lead to improved recognition performance, and that segmentation of speech into sentence-like units has an impact on parser performance. This paper brings these two findings together, showing that segmentation also impacts the quality of a syntax-based language model, such that larger reductions in word error rate are possible when using sentence-like segmentations rather than simple paused-based strategies. Further, we show that the same types of syntactic features used in parse reranking can also be used to reduce word error rate in an N-best rescoring framework.