Joint reranking of parsing and word recognition with automatic segmentation☆

Publication year: 2012
Source: Computer Speech & Language, Volume 26, Issue 1, January 2012, Pages 1-19

Jeremy G., Kahn , Mari, Ostendorf

 Abstract: Evaluation and optimization of automatic speech recognition (ASR) and parsing systems are often done separately. In the context of spoken language processing, however, these problems may be explored jointly via a reranking architecture. In this work, the effects of reranking for word error rate (WER) or reranking for the Sparseval parse-quality measure are examined in conversational speech recognition, while considering the impact of automatic segmentation. Under a WER criterion, the results indicate that the parse language model alone provides little benefit over a large n-gram model, but adding non-local syntactic features leads to improved performance. Under a Sparseval criterion, it…

 Highlights: ► A new framework for joint reranking of parsing and word recognition incorporating automatic sentence segmentation. ► Confirms prior findings: segmentation quality has impact on parsing (Sparseval) quality; parsing language model has word error rate (WER) impact. ► Non-local syntactic features in reranking yield WER improvements vs. parsing LM alone; benefits larger when optimizing for WER (vs. parsing). ► More alternate word-hypotheses in reranking have a larger impact on parse accuracy than more parse hypotheses, and. ► Significant gains in parse accuracy are obtained through joint optimization.