Matches in SemOpenAlex for { <https://semopenalex.org/work/W2952911134> ?p ?o ?g. }
Showing items 1 to 86 of
86
with 100 items per page.
- W2952911134 abstract "In topic identification (topic ID) on real-world unstructured audio, an audio instance of variable topic shifts is first broken into sequential segments, and each segment is independently classified. We first present a general purpose method for topic ID on spoken segments in low-resource languages, using a cascade of universal acoustic modeling, translation lexicons to English, and English-language topic classification. Next, instead of classifying each segment independently, we demonstrate that exploring the contextual dependencies across sequential segments can provide large improvements. In particular, we propose an attention-based contextual model which is able to leverage the contexts in a selective manner. We test both our contextual and non-contextual models on four LORELEI languages, and on all but one our attention-based contextual model significantly outperforms the context-independent models." @default.
- W2952911134 created "2019-06-27" @default.
- W2952911134 creator A5001291873 @default.
- W2952911134 creator A5014455067 @default.
- W2952911134 creator A5014580424 @default.
- W2952911134 creator A5017882589 @default.
- W2952911134 creator A5050632169 @default.
- W2952911134 creator A5069296252 @default.
- W2952911134 creator A5089639077 @default.
- W2952911134 date "2018-07-17" @default.
- W2952911134 modified "2023-09-26" @default.
- W2952911134 title "Low-Resource Contextual Topic Identification on Speech" @default.
- W2952911134 cites W1586532344 @default.
- W2952911134 cites W2130180273 @default.
- W2952911134 cites W2142623206 @default.
- W2952911134 cites W2147152072 @default.
- W2952911134 cites W2156985047 @default.
- W2952911134 cites W2169724380 @default.
- W2952911134 cites W2219249508 @default.
- W2952911134 cites W2251939518 @default.
- W2952911134 cites W2402146185 @default.
- W2952911134 cites W2573062194 @default.
- W2952911134 cites W2586568968 @default.
- W2952911134 cites W2626778328 @default.
- W2952911134 cites W2747994726 @default.
- W2952911134 cites W2949541494 @default.
- W2952911134 cites W2964121744 @default.
- W2952911134 cites W2964308564 @default.
- W2952911134 cites W66167291 @default.
- W2952911134 doi "https://doi.org/10.48550/arxiv.1807.06204" @default.
- W2952911134 hasPublicationYear "2018" @default.
- W2952911134 type Work @default.
- W2952911134 sameAs 2952911134 @default.
- W2952911134 citedByCount "0" @default.
- W2952911134 crossrefType "posted-content" @default.
- W2952911134 hasAuthorship W2952911134A5001291873 @default.
- W2952911134 hasAuthorship W2952911134A5014455067 @default.
- W2952911134 hasAuthorship W2952911134A5014580424 @default.
- W2952911134 hasAuthorship W2952911134A5017882589 @default.
- W2952911134 hasAuthorship W2952911134A5050632169 @default.
- W2952911134 hasAuthorship W2952911134A5069296252 @default.
- W2952911134 hasAuthorship W2952911134A5089639077 @default.
- W2952911134 hasBestOaLocation W29529111341 @default.
- W2952911134 hasConcept C116834253 @default.
- W2952911134 hasConcept C137293760 @default.
- W2952911134 hasConcept C151730666 @default.
- W2952911134 hasConcept C153083717 @default.
- W2952911134 hasConcept C154945302 @default.
- W2952911134 hasConcept C204321447 @default.
- W2952911134 hasConcept C2779343474 @default.
- W2952911134 hasConcept C2781238097 @default.
- W2952911134 hasConcept C28490314 @default.
- W2952911134 hasConcept C41008148 @default.
- W2952911134 hasConcept C59822182 @default.
- W2952911134 hasConcept C71611378 @default.
- W2952911134 hasConcept C86803240 @default.
- W2952911134 hasConceptScore W2952911134C116834253 @default.
- W2952911134 hasConceptScore W2952911134C137293760 @default.
- W2952911134 hasConceptScore W2952911134C151730666 @default.
- W2952911134 hasConceptScore W2952911134C153083717 @default.
- W2952911134 hasConceptScore W2952911134C154945302 @default.
- W2952911134 hasConceptScore W2952911134C204321447 @default.
- W2952911134 hasConceptScore W2952911134C2779343474 @default.
- W2952911134 hasConceptScore W2952911134C2781238097 @default.
- W2952911134 hasConceptScore W2952911134C28490314 @default.
- W2952911134 hasConceptScore W2952911134C41008148 @default.
- W2952911134 hasConceptScore W2952911134C59822182 @default.
- W2952911134 hasConceptScore W2952911134C71611378 @default.
- W2952911134 hasConceptScore W2952911134C86803240 @default.
- W2952911134 hasLocation W29529111341 @default.
- W2952911134 hasOpenAccess W2952911134 @default.
- W2952911134 hasPrimaryLocation W29529111341 @default.
- W2952911134 hasRelatedWork W1989705153 @default.
- W2952911134 hasRelatedWork W2293457016 @default.
- W2952911134 hasRelatedWork W2351428524 @default.
- W2952911134 hasRelatedWork W2359001871 @default.
- W2952911134 hasRelatedWork W2368779261 @default.
- W2952911134 hasRelatedWork W2496228846 @default.
- W2952911134 hasRelatedWork W2789919619 @default.
- W2952911134 hasRelatedWork W2896411932 @default.
- W2952911134 hasRelatedWork W3169305685 @default.
- W2952911134 hasRelatedWork W4296285654 @default.
- W2952911134 isParatext "false" @default.
- W2952911134 isRetracted "false" @default.
- W2952911134 magId "2952911134" @default.
- W2952911134 workType "article" @default.