logo Idiap Research Institute        
 [BibTeX] [Marc21]
Pseudo-Syntactic Language Modeling for Disfluent Speech Recognition
Type of publication: Conference paper
Citation: McGreevy04b
Booktitle: Proceedings of SST 2004 (10th Australian International Conference on Speech Science & Technology,',','), Sydney, Australia, 2004
Year: 2004
Month: 12
Note: IDIAP-RR 04-55
Crossref: mcgreevy04a:
Abstract: 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.
Userfields: ipdmembership={speech},
Keywords:
Projects Idiap
Authors McGreevy, Michael
Added by: [UNK]
Total mark: 0
Attachments
  • mcgreevy-sst04.pdf
  • mcgreevy-sst04.ps.gz
Notes