Matches in SemOpenAlex for { <https://semopenalex.org/work/W14656806> ?p ?o ?g. }
- W14656806 abstract "Most conversational understanding (CU) systems today employ a cascade approach, where the best hypothesis from automatic speech recognizer (ASR) is fed into spoken language understanding (SLU) module, whose best hypothesis is then fed into other systems such as interpreter or dialog manager. In such approaches, errors from one statistical module irreversibly propagates into another module causing a serious degradation in the overall performance of the conversational understanding system. Thus it is desirable to jointly optimize all the statistical modules together. As a first step towards this, in this paper, we propose a joint decoding framework in which we predict the optimal word as well as slot (semantic tag) sequence jointly given the input acoustic stream. On Microsoft’s CU system, we show 1.3% absolute reduction in word error rate (WER) and 1.2% absolute improvement in F measure for slot prediction when compared to a very strong cascade baseline comprising of the state-of-the-art recognizer followed by a slot sequence tagger." @default.
- W14656806 created "2016-06-24" @default.
- W14656806 creator A5000621526 @default.
- W14656806 creator A5068709817 @default.
- W14656806 creator A5072875068 @default.
- W14656806 creator A5087941479 @default.
- W14656806 date "2012-09-09" @default.
- W14656806 modified "2023-09-30" @default.
- W14656806 title "Joint decoding for speech recognition and semantic tagging" @default.
- W14656806 cites W1582482241 @default.
- W14656806 cites W169943709 @default.
- W14656806 cites W1768132882 @default.
- W14656806 cites W2007080341 @default.
- W14656806 cites W2007261869 @default.
- W14656806 cites W2142904027 @default.
- W14656806 cites W2147880316 @default.
- W14656806 cites W2149980590 @default.
- W14656806 cites W2150859660 @default.
- W14656806 cites W2158873310 @default.
- W14656806 cites W2160986985 @default.
- W14656806 doi "https://doi.org/10.21437/interspeech.2012-324" @default.
- W14656806 hasPublicationYear "2012" @default.
- W14656806 type Work @default.
- W14656806 sameAs 14656806 @default.
- W14656806 citedByCount "17" @default.
- W14656806 countsByYear W146568062012 @default.
- W14656806 countsByYear W146568062013 @default.
- W14656806 countsByYear W146568062014 @default.
- W14656806 countsByYear W146568062015 @default.
- W14656806 countsByYear W146568062016 @default.
- W14656806 countsByYear W146568062017 @default.
- W14656806 countsByYear W146568062020 @default.
- W14656806 countsByYear W146568062022 @default.
- W14656806 countsByYear W146568062023 @default.
- W14656806 crossrefType "proceedings-article" @default.
- W14656806 hasAuthorship W14656806A5000621526 @default.
- W14656806 hasAuthorship W14656806A5068709817 @default.
- W14656806 hasAuthorship W14656806A5072875068 @default.
- W14656806 hasAuthorship W14656806A5087941479 @default.
- W14656806 hasConcept C105795698 @default.
- W14656806 hasConcept C11413529 @default.
- W14656806 hasConcept C124101348 @default.
- W14656806 hasConcept C127413603 @default.
- W14656806 hasConcept C136764020 @default.
- W14656806 hasConcept C137293760 @default.
- W14656806 hasConcept C138885662 @default.
- W14656806 hasConcept C154945302 @default.
- W14656806 hasConcept C170154142 @default.
- W14656806 hasConcept C173853756 @default.
- W14656806 hasConcept C18555067 @default.
- W14656806 hasConcept C185592680 @default.
- W14656806 hasConcept C18653775 @default.
- W14656806 hasConcept C204321447 @default.
- W14656806 hasConcept C23224414 @default.
- W14656806 hasConcept C2778112365 @default.
- W14656806 hasConcept C2780009758 @default.
- W14656806 hasConcept C28490314 @default.
- W14656806 hasConcept C33923547 @default.
- W14656806 hasConcept C34146451 @default.
- W14656806 hasConcept C40969351 @default.
- W14656806 hasConcept C41008148 @default.
- W14656806 hasConcept C41895202 @default.
- W14656806 hasConcept C43617362 @default.
- W14656806 hasConcept C54355233 @default.
- W14656806 hasConcept C57273362 @default.
- W14656806 hasConcept C86803240 @default.
- W14656806 hasConcept C90805587 @default.
- W14656806 hasConceptScore W14656806C105795698 @default.
- W14656806 hasConceptScore W14656806C11413529 @default.
- W14656806 hasConceptScore W14656806C124101348 @default.
- W14656806 hasConceptScore W14656806C127413603 @default.
- W14656806 hasConceptScore W14656806C136764020 @default.
- W14656806 hasConceptScore W14656806C137293760 @default.
- W14656806 hasConceptScore W14656806C138885662 @default.
- W14656806 hasConceptScore W14656806C154945302 @default.
- W14656806 hasConceptScore W14656806C170154142 @default.
- W14656806 hasConceptScore W14656806C173853756 @default.
- W14656806 hasConceptScore W14656806C18555067 @default.
- W14656806 hasConceptScore W14656806C185592680 @default.
- W14656806 hasConceptScore W14656806C18653775 @default.
- W14656806 hasConceptScore W14656806C204321447 @default.
- W14656806 hasConceptScore W14656806C23224414 @default.
- W14656806 hasConceptScore W14656806C2778112365 @default.
- W14656806 hasConceptScore W14656806C2780009758 @default.
- W14656806 hasConceptScore W14656806C28490314 @default.
- W14656806 hasConceptScore W14656806C33923547 @default.
- W14656806 hasConceptScore W14656806C34146451 @default.
- W14656806 hasConceptScore W14656806C40969351 @default.
- W14656806 hasConceptScore W14656806C41008148 @default.
- W14656806 hasConceptScore W14656806C41895202 @default.
- W14656806 hasConceptScore W14656806C43617362 @default.
- W14656806 hasConceptScore W14656806C54355233 @default.
- W14656806 hasConceptScore W14656806C57273362 @default.
- W14656806 hasConceptScore W14656806C86803240 @default.
- W14656806 hasConceptScore W14656806C90805587 @default.
- W14656806 hasLocation W146568061 @default.
- W14656806 hasOpenAccess W14656806 @default.
- W14656806 hasPrimaryLocation W146568061 @default.
- W14656806 hasRelatedWork W108044715 @default.
- W14656806 hasRelatedWork W1574174742 @default.