Matches in SemOpenAlex for { <https://semopenalex.org/work/W85853872> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W85853872 abstract "In language modeling for speech recognition the goal is to constrain the search of the speech recognizer by providing a model which can, a context, indicate what the next most likely word will be. In this paper, we explore how the addition of information to the text, in particular part of speech and dysfluency annotations, can be used to,build more complex language models. In particular, we ask two questions. First, in conversational speech, where there is a less clear notion of than in written text, does segmenting the text into linguistically or semantically based units contribute to a better language model than merely segmenting based on broad acoustic information, such as pauses. Second, is the sentence itself a good unit to be modeling, or should we look at smaller units, for example, dividing a sentence into a given and new portion and segmenting out acknowledgments and replies. To answer these questions, we present a variety of kinds of analysis, from vocabulary distributions to perplexities on language models. The next step will be modeling conversations and incorporating those models into a speech recognizer." @default.
- W85853872 created "2016-06-24" @default.
- W85853872 creator A5000529247 @default.
- W85853872 creator A5066207492 @default.
- W85853872 date "1996-01-01" @default.
- W85853872 modified "2023-09-25" @default.
- W85853872 title "Modeling Conversational Speech for Speech Recognition" @default.
- W85853872 cites W1990387894 @default.
- W85853872 cites W2015933299 @default.
- W85853872 cites W2134237567 @default.
- W85853872 cites W2166637769 @default.
- W85853872 hasPublicationYear "1996" @default.
- W85853872 type Work @default.
- W85853872 sameAs 85853872 @default.
- W85853872 citedByCount "17" @default.
- W85853872 countsByYear W858538722017 @default.
- W85853872 countsByYear W858538722018 @default.
- W85853872 countsByYear W858538722021 @default.
- W85853872 crossrefType "proceedings-article" @default.
- W85853872 hasAuthorship W85853872A5000529247 @default.
- W85853872 hasAuthorship W85853872A5066207492 @default.
- W85853872 hasConcept C125308379 @default.
- W85853872 hasConcept C136197465 @default.
- W85853872 hasConcept C137293760 @default.
- W85853872 hasConcept C138885662 @default.
- W85853872 hasConcept C144133560 @default.
- W85853872 hasConcept C151730666 @default.
- W85853872 hasConcept C154945302 @default.
- W85853872 hasConcept C162853370 @default.
- W85853872 hasConcept C204321447 @default.
- W85853872 hasConcept C2777530160 @default.
- W85853872 hasConcept C2777601683 @default.
- W85853872 hasConcept C2779343474 @default.
- W85853872 hasConcept C28490314 @default.
- W85853872 hasConcept C41008148 @default.
- W85853872 hasConcept C41895202 @default.
- W85853872 hasConcept C86803240 @default.
- W85853872 hasConceptScore W85853872C125308379 @default.
- W85853872 hasConceptScore W85853872C136197465 @default.
- W85853872 hasConceptScore W85853872C137293760 @default.
- W85853872 hasConceptScore W85853872C138885662 @default.
- W85853872 hasConceptScore W85853872C144133560 @default.
- W85853872 hasConceptScore W85853872C151730666 @default.
- W85853872 hasConceptScore W85853872C154945302 @default.
- W85853872 hasConceptScore W85853872C162853370 @default.
- W85853872 hasConceptScore W85853872C204321447 @default.
- W85853872 hasConceptScore W85853872C2777530160 @default.
- W85853872 hasConceptScore W85853872C2777601683 @default.
- W85853872 hasConceptScore W85853872C2779343474 @default.
- W85853872 hasConceptScore W85853872C28490314 @default.
- W85853872 hasConceptScore W85853872C41008148 @default.
- W85853872 hasConceptScore W85853872C41895202 @default.
- W85853872 hasConceptScore W85853872C86803240 @default.
- W85853872 hasLocation W858538721 @default.
- W85853872 hasOpenAccess W85853872 @default.
- W85853872 hasPrimaryLocation W858538721 @default.
- W85853872 hasRelatedWork W1504308419 @default.
- W85853872 hasRelatedWork W1567708560 @default.
- W85853872 hasRelatedWork W1571920584 @default.
- W85853872 hasRelatedWork W166347353 @default.
- W85853872 hasRelatedWork W1995735257 @default.
- W85853872 hasRelatedWork W2056211539 @default.
- W85853872 hasRelatedWork W2066051122 @default.
- W85853872 hasRelatedWork W2078578680 @default.
- W85853872 hasRelatedWork W2124246394 @default.
- W85853872 hasRelatedWork W2163194113 @default.
- W85853872 hasRelatedWork W2166637769 @default.
- W85853872 hasRelatedWork W2183734687 @default.
- W85853872 hasRelatedWork W3207236467 @default.
- W85853872 hasRelatedWork W636660833 @default.
- W85853872 hasRelatedWork W2189430436 @default.
- W85853872 hasRelatedWork W2560872329 @default.
- W85853872 hasRelatedWork W2562544104 @default.
- W85853872 hasRelatedWork W2777268945 @default.
- W85853872 hasRelatedWork W3001679544 @default.
- W85853872 hasRelatedWork W3144021024 @default.
- W85853872 isParatext "false" @default.
- W85853872 isRetracted "false" @default.
- W85853872 magId "85853872" @default.
- W85853872 workType "article" @default.