Matches in SemOpenAlex for { <https://semopenalex.org/work/W201960594> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W201960594 abstract "We present a multi-pass approach to real-time, largevocabulary speech recognition in which we dynamically manipulate the vocabulary between passes. For recognition tasks where subsets of the vocabulary can be triggered by the occurences of other words or phrases, a combination of unknown word modelling and vocabulary refinement can be utilized to attack large-vocabulary tasks with relatively small active vocabularies. We evaluate this approach within the JUPITERweather information domain by enabling recognition of all 30,000 citystate pairs within the USA. By maximally precompiling the static and dynamic portions of our search space using finitestate transducers (FSTs), we splice dynamic-vocabulary components on-demand during decoding with negligible speed impact while enforcing cross-word context-dependent constraints. We find that a dynamic-vocabulary system can compete quite favorably with a single-pass, large-vocabulary system. For even larger vocabularies (e.g., street addresses), static compilation may be infeasible, making a dynamic-vocabulary approach necessary." @default.
- W201960594 created "2016-06-24" @default.
- W201960594 creator A5057112113 @default.
- W201960594 date "2005-09-04" @default.
- W201960594 modified "2023-09-26" @default.
- W201960594 title "A multi-pass, dynamic-vocabulary approach to real-time, large-vocabulary speech recognition" @default.
- W201960594 cites W1480656021 @default.
- W201960594 cites W1501139663 @default.
- W201960594 cites W1505369858 @default.
- W201960594 cites W1625762979 @default.
- W201960594 cites W200335640 @default.
- W201960594 cites W2100373303 @default.
- W201960594 cites W2111732304 @default.
- W201960594 cites W2118375831 @default.
- W201960594 cites W2130607791 @default.
- W201960594 cites W2162432783 @default.
- W201960594 cites W302089799 @default.
- W201960594 cites W332538731 @default.
- W201960594 doi "https://doi.org/10.21437/interspeech.2005-337" @default.
- W201960594 hasPublicationYear "2005" @default.
- W201960594 type Work @default.
- W201960594 sameAs 201960594 @default.
- W201960594 citedByCount "12" @default.
- W201960594 countsByYear W2019605942012 @default.
- W201960594 countsByYear W2019605942013 @default.
- W201960594 crossrefType "proceedings-article" @default.
- W201960594 hasAuthorship W201960594A5057112113 @default.
- W201960594 hasConcept C134306372 @default.
- W201960594 hasConcept C138885662 @default.
- W201960594 hasConcept C151730666 @default.
- W201960594 hasConcept C154945302 @default.
- W201960594 hasConcept C204321447 @default.
- W201960594 hasConcept C2777601683 @default.
- W201960594 hasConcept C2779343474 @default.
- W201960594 hasConcept C28490314 @default.
- W201960594 hasConcept C33923547 @default.
- W201960594 hasConcept C36503486 @default.
- W201960594 hasConcept C41008148 @default.
- W201960594 hasConcept C41895202 @default.
- W201960594 hasConcept C86803240 @default.
- W201960594 hasConcept C90805587 @default.
- W201960594 hasConceptScore W201960594C134306372 @default.
- W201960594 hasConceptScore W201960594C138885662 @default.
- W201960594 hasConceptScore W201960594C151730666 @default.
- W201960594 hasConceptScore W201960594C154945302 @default.
- W201960594 hasConceptScore W201960594C204321447 @default.
- W201960594 hasConceptScore W201960594C2777601683 @default.
- W201960594 hasConceptScore W201960594C2779343474 @default.
- W201960594 hasConceptScore W201960594C28490314 @default.
- W201960594 hasConceptScore W201960594C33923547 @default.
- W201960594 hasConceptScore W201960594C36503486 @default.
- W201960594 hasConceptScore W201960594C41008148 @default.
- W201960594 hasConceptScore W201960594C41895202 @default.
- W201960594 hasConceptScore W201960594C86803240 @default.
- W201960594 hasConceptScore W201960594C90805587 @default.
- W201960594 hasLocation W2019605941 @default.
- W201960594 hasOpenAccess W201960594 @default.
- W201960594 hasPrimaryLocation W2019605941 @default.
- W201960594 hasRelatedWork W11531451 @default.
- W201960594 hasRelatedWork W1552159754 @default.
- W201960594 hasRelatedWork W2151447942 @default.
- W201960594 hasRelatedWork W2293457016 @default.
- W201960594 hasRelatedWork W2368651715 @default.
- W201960594 hasRelatedWork W2611614995 @default.
- W201960594 hasRelatedWork W2789919619 @default.
- W201960594 hasRelatedWork W2900389025 @default.
- W201960594 hasRelatedWork W3107474891 @default.
- W201960594 hasRelatedWork W3169305685 @default.
- W201960594 isParatext "false" @default.
- W201960594 isRetracted "false" @default.
- W201960594 magId "201960594" @default.
- W201960594 workType "article" @default.