Matches in SemOpenAlex for { <https://semopenalex.org/work/W2045309213> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2045309213 abstract "Automatic sentence segmentation of speech is important for enriching speech recognition output and aiding downstream language processing. This paper focuses on automatic sentence segmentation of speech in two different languages - English and Czech. For this task, we compare and combine three statistical models - HMM, maximum entropy, and a boosting-based model BoosTexter. All these approaches rely on both textual and prosodic information. We evaluate these methods on a corpus of multiparty meetings in English, and on a corpus of broadcast conversations in Czech, using both manual and speech recognition transcripts. The experiments show that superior results are achieved when all the three models are combined via posterior probability interpolation. We observe differences in terms of model performance between English and Czech, as well as the feature usage difference in prosodic models between the two languages. Overall, the analysis is important for porting sentence segmentation approaches from one language to another." @default.
- W2045309213 created "2016-06-24" @default.
- W2045309213 creator A5023363049 @default.
- W2045309213 creator A5082021449 @default.
- W2045309213 date "2010-03-01" @default.
- W2045309213 modified "2023-09-22" @default.
- W2045309213 title "Automatic sentence boundary detection in conversational speech: A cross-lingual evaluation on English and Czech" @default.
- W2045309213 cites W1526024327 @default.
- W2045309213 cites W1575895314 @default.
- W2045309213 cites W1591607137 @default.
- W2045309213 cites W1595011599 @default.
- W2045309213 cites W1922346566 @default.
- W2045309213 cites W2001068000 @default.
- W2045309213 cites W2053463056 @default.
- W2045309213 cites W2072776834 @default.
- W2045309213 cites W2122811611 @default.
- W2045309213 cites W2153797513 @default.
- W2045309213 cites W2161274063 @default.
- W2045309213 cites W2426479676 @default.
- W2045309213 cites W94670513 @default.
- W2045309213 doi "https://doi.org/10.1109/icassp.2010.5494976" @default.
- W2045309213 hasPublicationYear "2010" @default.
- W2045309213 type Work @default.
- W2045309213 sameAs 2045309213 @default.
- W2045309213 citedByCount "9" @default.
- W2045309213 countsByYear W20453092132013 @default.
- W2045309213 countsByYear W20453092132014 @default.
- W2045309213 countsByYear W20453092132016 @default.
- W2045309213 countsByYear W20453092132017 @default.
- W2045309213 countsByYear W20453092132020 @default.
- W2045309213 countsByYear W20453092132022 @default.
- W2045309213 crossrefType "proceedings-article" @default.
- W2045309213 hasAuthorship W2045309213A5023363049 @default.
- W2045309213 hasAuthorship W2045309213A5082021449 @default.
- W2045309213 hasBestOaLocation W20453092132 @default.
- W2045309213 hasConcept C137293760 @default.
- W2045309213 hasConcept C138885662 @default.
- W2045309213 hasConcept C154945302 @default.
- W2045309213 hasConcept C204321447 @default.
- W2045309213 hasConcept C23224414 @default.
- W2045309213 hasConcept C2776401178 @default.
- W2045309213 hasConcept C2777530160 @default.
- W2045309213 hasConcept C2777842544 @default.
- W2045309213 hasConcept C28490314 @default.
- W2045309213 hasConcept C41008148 @default.
- W2045309213 hasConcept C41895202 @default.
- W2045309213 hasConcept C61328038 @default.
- W2045309213 hasConcept C89600930 @default.
- W2045309213 hasConceptScore W2045309213C137293760 @default.
- W2045309213 hasConceptScore W2045309213C138885662 @default.
- W2045309213 hasConceptScore W2045309213C154945302 @default.
- W2045309213 hasConceptScore W2045309213C204321447 @default.
- W2045309213 hasConceptScore W2045309213C23224414 @default.
- W2045309213 hasConceptScore W2045309213C2776401178 @default.
- W2045309213 hasConceptScore W2045309213C2777530160 @default.
- W2045309213 hasConceptScore W2045309213C2777842544 @default.
- W2045309213 hasConceptScore W2045309213C28490314 @default.
- W2045309213 hasConceptScore W2045309213C41008148 @default.
- W2045309213 hasConceptScore W2045309213C41895202 @default.
- W2045309213 hasConceptScore W2045309213C61328038 @default.
- W2045309213 hasConceptScore W2045309213C89600930 @default.
- W2045309213 hasLocation W20453092131 @default.
- W2045309213 hasLocation W20453092132 @default.
- W2045309213 hasLocation W20453092133 @default.
- W2045309213 hasOpenAccess W2045309213 @default.
- W2045309213 hasPrimaryLocation W20453092131 @default.
- W2045309213 hasRelatedWork W177166743 @default.
- W2045309213 hasRelatedWork W2110188288 @default.
- W2045309213 hasRelatedWork W2118515477 @default.
- W2045309213 hasRelatedWork W2315947091 @default.
- W2045309213 hasRelatedWork W2349075084 @default.
- W2045309213 hasRelatedWork W2374918184 @default.
- W2045309213 hasRelatedWork W2793122029 @default.
- W2045309213 hasRelatedWork W3107474891 @default.
- W2045309213 hasRelatedWork W39836914 @default.
- W2045309213 hasRelatedWork W4214818988 @default.
- W2045309213 isParatext "false" @default.
- W2045309213 isRetracted "false" @default.
- W2045309213 magId "2045309213" @default.
- W2045309213 workType "article" @default.