Matches in SemOpenAlex for { <https://semopenalex.org/work/W2079359534> ?p ?o ?g. }
- W2079359534 abstract "This paper proposes a discriminative learning algorithm for improving the accuracy of continuous speech recognition systems through optimizing the language model parameters on decoding graphs. The proposed algorithm employs soft margin estimation (SME) to build an objective function for maximizing the margin between the correct transcriptions and the corresponding competing hypotheses. To this end, we adapted a discriminative training procedure based on SME, which is originally devised for optimizing acoustic models, to a different case of optimizing the parameters of language models on a decoding graph constructed using weighted finite-state transducers. Experimental results show that the proposed algorithm outperforms a baseline system based on the maximum likelihood estimation and achieves a reduction of 15.11% relative word error rate when tested on the Resource Management (RM1) database." @default.
- W2079359534 created "2016-06-24" @default.
- W2079359534 creator A5031054535 @default.
- W2079359534 creator A5043619920 @default.
- W2079359534 date "2013-10-01" @default.
- W2079359534 modified "2023-09-26" @default.
- W2079359534 title "Optimization on decoding graphs using soft margin estimation" @default.
- W2079359534 cites W1534604906 @default.
- W2079359534 cites W1877570817 @default.
- W2079359534 cites W191444391 @default.
- W2079359534 cites W1968424304 @default.
- W2079359534 cites W1997539970 @default.
- W2079359534 cites W2005076803 @default.
- W2079359534 cites W2020144989 @default.
- W2079359534 cites W2046932483 @default.
- W2079359534 cites W2093478938 @default.
- W2079359534 cites W2097003869 @default.
- W2079359534 cites W2111479622 @default.
- W2079359534 cites W2124445791 @default.
- W2079359534 cites W2148357004 @default.
- W2079359534 cites W2150907703 @default.
- W2079359534 cites W2154075111 @default.
- W2079359534 cites W2154681956 @default.
- W2079359534 cites W2158069733 @default.
- W2079359534 cites W2159112514 @default.
- W2079359534 cites W2168077532 @default.
- W2079359534 cites W2322283567 @default.
- W2079359534 cites W2399937137 @default.
- W2079359534 cites W27187656 @default.
- W2079359534 cites W30564313 @default.
- W2079359534 cites W3149335959 @default.
- W2079359534 doi "https://doi.org/10.1109/apsipa.2013.6694226" @default.
- W2079359534 hasPublicationYear "2013" @default.
- W2079359534 type Work @default.
- W2079359534 sameAs 2079359534 @default.
- W2079359534 citedByCount "0" @default.
- W2079359534 crossrefType "proceedings-article" @default.
- W2079359534 hasAuthorship W2079359534A5031054535 @default.
- W2079359534 hasAuthorship W2079359534A5043619920 @default.
- W2079359534 hasConcept C111335779 @default.
- W2079359534 hasConcept C111368507 @default.
- W2079359534 hasConcept C11413529 @default.
- W2079359534 hasConcept C119857082 @default.
- W2079359534 hasConcept C12725497 @default.
- W2079359534 hasConcept C127313418 @default.
- W2079359534 hasConcept C132525143 @default.
- W2079359534 hasConcept C137293760 @default.
- W2079359534 hasConcept C153180895 @default.
- W2079359534 hasConcept C154945302 @default.
- W2079359534 hasConcept C2524010 @default.
- W2079359534 hasConcept C28490314 @default.
- W2079359534 hasConcept C33923547 @default.
- W2079359534 hasConcept C40969351 @default.
- W2079359534 hasConcept C41008148 @default.
- W2079359534 hasConcept C57273362 @default.
- W2079359534 hasConcept C774472 @default.
- W2079359534 hasConcept C80444323 @default.
- W2079359534 hasConcept C97931131 @default.
- W2079359534 hasConceptScore W2079359534C111335779 @default.
- W2079359534 hasConceptScore W2079359534C111368507 @default.
- W2079359534 hasConceptScore W2079359534C11413529 @default.
- W2079359534 hasConceptScore W2079359534C119857082 @default.
- W2079359534 hasConceptScore W2079359534C12725497 @default.
- W2079359534 hasConceptScore W2079359534C127313418 @default.
- W2079359534 hasConceptScore W2079359534C132525143 @default.
- W2079359534 hasConceptScore W2079359534C137293760 @default.
- W2079359534 hasConceptScore W2079359534C153180895 @default.
- W2079359534 hasConceptScore W2079359534C154945302 @default.
- W2079359534 hasConceptScore W2079359534C2524010 @default.
- W2079359534 hasConceptScore W2079359534C28490314 @default.
- W2079359534 hasConceptScore W2079359534C33923547 @default.
- W2079359534 hasConceptScore W2079359534C40969351 @default.
- W2079359534 hasConceptScore W2079359534C41008148 @default.
- W2079359534 hasConceptScore W2079359534C57273362 @default.
- W2079359534 hasConceptScore W2079359534C774472 @default.
- W2079359534 hasConceptScore W2079359534C80444323 @default.
- W2079359534 hasConceptScore W2079359534C97931131 @default.
- W2079359534 hasLocation W20793595341 @default.
- W2079359534 hasOpenAccess W2079359534 @default.
- W2079359534 hasPrimaryLocation W20793595341 @default.
- W2079359534 hasRelatedWork W1499618803 @default.
- W2079359534 hasRelatedWork W1605997703 @default.
- W2079359534 hasRelatedWork W1765418723 @default.
- W2079359534 hasRelatedWork W1975953721 @default.
- W2079359534 hasRelatedWork W2012963025 @default.
- W2079359534 hasRelatedWork W2018853752 @default.
- W2079359534 hasRelatedWork W2096075540 @default.
- W2079359534 hasRelatedWork W2097635532 @default.
- W2079359534 hasRelatedWork W2100169672 @default.
- W2079359534 hasRelatedWork W2111033738 @default.
- W2079359534 hasRelatedWork W2120098943 @default.
- W2079359534 hasRelatedWork W2121986117 @default.
- W2079359534 hasRelatedWork W2124707525 @default.
- W2079359534 hasRelatedWork W2146049072 @default.
- W2079359534 hasRelatedWork W2171244697 @default.
- W2079359534 hasRelatedWork W2318207009 @default.
- W2079359534 hasRelatedWork W2400584550 @default.
- W2079359534 hasRelatedWork W2500011979 @default.
- W2079359534 hasRelatedWork W2615025407 @default.
- W2079359534 hasRelatedWork W1785663456 @default.