Paper: Using Chunk Based Partial Parsing of Spontaneous Speech in Unrestricted Domains for Reducing Word Error Rate in Speech Recognition

ACL ID P98-2237
Title Using Chunk Based Partial Parsing of Spontaneous Speech in Unrestricted Domains for Reducing Word Error Rate in Speech Recognition
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 1998
Authors

In this paper, we present a chunk based partial pars- ing system for spontaneous, conversational speech in unrestricted domains. We show that the chunk parses produced by this parsing system can be use- fully applied to the task of reranking Nbest lists from a speech recognizer, using a combination of chunk-based n-gram model scores and chunk cov- erage scores. The input for the system is Nbest lists generated from speech recognizer lattices. The hypotheses from the Nbest lists are tagged for part of speech, "cleaned up" by a preprocessing pipe, parsed by a part of speech based chunk parser, and rescored using a backpropagation neural net trained on the chunk based scores. Finally, the reranked Nbest lists are generated. The results of a system evaluation are promising in that a chunk accu...