Matches in SemOpenAlex for { <https://semopenalex.org/work/W173678734> ?p ?o ?g. }
Showing items 1 to 55 of
55
with 100 items per page.
- W173678734 abstract "The word graphs produced by a large vocabulary speech recognition system usually contain a path labelled with the correct utterance, but this is not always the highest scoring path. Boosting increases the probability of words which occur often in the word graph, which are in some sense robust. Adding syntactic information allows rescoring of arc probabilities with the possibility that more grammarical word sequences will also be the correct ones. A theory is developed which allows general probabilistic syntactic models to be used to rescore word lattices. Experiments conducted on the Wall Street Journal (WSJ) corpus with a version of the AT&T 1995 FST LVSR system with part of speech (POS) trigram sequences show that using only POS leads to a loss in performance. Boosting alone provides an improvement in performance which is not statistically significant. Cascading the two methods, boosting first and then using syntactic information improves performance 4.5 % relative on a large portion of the 1995 DARPA test set." @default.
- W173678734 created "2016-06-24" @default.
- W173678734 creator A5029120633 @default.
- W173678734 creator A5048574769 @default.
- W173678734 date "2001-09-03" @default.
- W173678734 modified "2023-10-18" @default.
- W173678734 title "Using boosting and POS word graph tagging to improve speech recognition" @default.
- W173678734 cites W1967165764 @default.
- W173678734 cites W2061271742 @default.
- W173678734 cites W2101920689 @default.
- W173678734 cites W2111041233 @default.
- W173678734 cites W2120011233 @default.
- W173678734 cites W2125529971 @default.
- W173678734 cites W2495567655 @default.
- W173678734 cites W2734606845 @default.
- W173678734 cites W70955329 @default.
- W173678734 doi "https://doi.org/10.21437/eurospeech.2001-505" @default.
- W173678734 hasPublicationYear "2001" @default.
- W173678734 type Work @default.
- W173678734 sameAs 173678734 @default.
- W173678734 citedByCount "0" @default.
- W173678734 crossrefType "proceedings-article" @default.
- W173678734 hasAuthorship W173678734A5029120633 @default.
- W173678734 hasAuthorship W173678734A5048574769 @default.
- W173678734 hasConcept C123406163 @default.
- W173678734 hasConcept C154945302 @default.
- W173678734 hasConcept C204321447 @default.
- W173678734 hasConcept C2780684714 @default.
- W173678734 hasConcept C28490314 @default.
- W173678734 hasConcept C41008148 @default.
- W173678734 hasConcept C46686674 @default.
- W173678734 hasConceptScore W173678734C123406163 @default.
- W173678734 hasConceptScore W173678734C154945302 @default.
- W173678734 hasConceptScore W173678734C204321447 @default.
- W173678734 hasConceptScore W173678734C2780684714 @default.
- W173678734 hasConceptScore W173678734C28490314 @default.
- W173678734 hasConceptScore W173678734C41008148 @default.
- W173678734 hasConceptScore W173678734C46686674 @default.
- W173678734 hasLocation W1736787341 @default.
- W173678734 hasOpenAccess W173678734 @default.
- W173678734 hasPrimaryLocation W1736787341 @default.
- W173678734 hasRelatedWork W102385157 @default.
- W173678734 hasRelatedWork W1549182469 @default.
- W173678734 hasRelatedWork W1965453504 @default.
- W173678734 hasRelatedWork W2169508526 @default.
- W173678734 hasRelatedWork W2251183413 @default.
- W173678734 hasRelatedWork W2369094010 @default.
- W173678734 hasRelatedWork W2486838646 @default.
- W173678734 hasRelatedWork W2891105353 @default.
- W173678734 hasRelatedWork W2902135563 @default.
- W173678734 hasRelatedWork W3107474891 @default.
- W173678734 isParatext "false" @default.
- W173678734 isRetracted "false" @default.
- W173678734 magId "173678734" @default.
- W173678734 workType "article" @default.