Matches in SemOpenAlex for { <https://semopenalex.org/work/W205010892> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W205010892 abstract "Spoken Language Understanding performs automatic concept labeling and segmentation of speech utterances. For this task, many approaches have been proposed based on both generative and discriminative models. While all these methods have shown remarkable accuracy on manual transcription of spoken utterances, robustness to noisy automatic transcription is still an open issue. In this paper we study algorithms for Spoken Language Understanding combining complementary learning models: Stochastic Finite State Transducers produce a list of hypotheses, which are re-ranked using a discriminative algorithm based on kernel methods. Our experiments on two different spoken dialog corpora, MEDIA and LUNA, show that the combined generative-discriminative model reaches the state-ofthe-art such as Conditional Random Fields (CRF) on manual transcriptions, and it is robust to noisy automatic transcriptions, outperforming, in some cases, the state-of-the-art." @default.
- W205010892 created "2016-06-24" @default.
- W205010892 creator A5050707731 @default.
- W205010892 creator A5056376686 @default.
- W205010892 creator A5062879885 @default.
- W205010892 date "2009-09-06" @default.
- W205010892 modified "2023-10-13" @default.
- W205010892 title "Concept segmentation and labeling for conversational speech" @default.
- W205010892 cites W1510073064 @default.
- W205010892 cites W1576520375 @default.
- W205010892 cites W1587871245 @default.
- W205010892 cites W1631260214 @default.
- W205010892 cites W1987486061 @default.
- W205010892 cites W2005267654 @default.
- W205010892 cites W2039387658 @default.
- W205010892 cites W2080922525 @default.
- W205010892 cites W2113322342 @default.
- W205010892 cites W2131297983 @default.
- W205010892 cites W2147880316 @default.
- W205010892 cites W21503661 @default.
- W205010892 cites W2156909104 @default.
- W205010892 cites W2158195707 @default.
- W205010892 cites W2166293310 @default.
- W205010892 cites W94225560 @default.
- W205010892 doi "https://doi.org/10.21437/interspeech.2009-702" @default.
- W205010892 hasPublicationYear "2009" @default.
- W205010892 type Work @default.
- W205010892 sameAs 205010892 @default.
- W205010892 citedByCount "14" @default.
- W205010892 countsByYear W2050108922012 @default.
- W205010892 countsByYear W2050108922015 @default.
- W205010892 countsByYear W2050108922017 @default.
- W205010892 countsByYear W2050108922019 @default.
- W205010892 countsByYear W2050108922020 @default.
- W205010892 crossrefType "proceedings-article" @default.
- W205010892 hasAuthorship W205010892A5050707731 @default.
- W205010892 hasAuthorship W205010892A5056376686 @default.
- W205010892 hasAuthorship W205010892A5062879885 @default.
- W205010892 hasConcept C154945302 @default.
- W205010892 hasConcept C204321447 @default.
- W205010892 hasConcept C28490314 @default.
- W205010892 hasConcept C41008148 @default.
- W205010892 hasConcept C61328038 @default.
- W205010892 hasConcept C89600930 @default.
- W205010892 hasConceptScore W205010892C154945302 @default.
- W205010892 hasConceptScore W205010892C204321447 @default.
- W205010892 hasConceptScore W205010892C28490314 @default.
- W205010892 hasConceptScore W205010892C41008148 @default.
- W205010892 hasConceptScore W205010892C61328038 @default.
- W205010892 hasConceptScore W205010892C89600930 @default.
- W205010892 hasLocation W2050108921 @default.
- W205010892 hasOpenAccess W205010892 @default.
- W205010892 hasPrimaryLocation W2050108921 @default.
- W205010892 hasRelatedWork W2110188288 @default.
- W205010892 hasRelatedWork W2118197055 @default.
- W205010892 hasRelatedWork W2144638120 @default.
- W205010892 hasRelatedWork W2333901563 @default.
- W205010892 hasRelatedWork W2518728926 @default.
- W205010892 hasRelatedWork W2612720144 @default.
- W205010892 hasRelatedWork W2738297198 @default.
- W205010892 hasRelatedWork W2999744382 @default.
- W205010892 hasRelatedWork W79237494 @default.
- W205010892 hasRelatedWork W2610625114 @default.
- W205010892 isParatext "false" @default.
- W205010892 isRetracted "false" @default.
- W205010892 magId "205010892" @default.
- W205010892 workType "article" @default.