Pseudo-Syntactic Language Modeling for Disfluent Speech Recognition

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.


Published in:
Proceedings of SST 2004 (10th Australian International Conference on Speech Science & Technology), Sydney, Australia, 2004
Presented at:
Proceedings of SST 2004 (10th Australian International Conference on Speech Science & Technology), Sydney, Australia, 2004
Year:
2004
Keywords:
Note:
IDIAP-RR 04-55
Laboratories:




 Record created 2006-03-10, last modified 2018-01-27

External links:
Download fulltextURL
Download fulltextRelated documents
Download fulltextn/a
Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)