Matches in SemOpenAlex for { <https://semopenalex.org/work/W2937649809> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2937649809 abstract "This paper describes a novel end-to-end automatic speech recognition (ASR) method that takes into consideration long-range sequential context information beyond utterance boundaries. In spontaneous ASR tasks such as those for discourses and conversations, the input speech often comprises a series of utterances. Accordingly, the relationships between the utterances should be leveraged for transcribing the individual utterances. While most previous end-to-end ASR methods only focus on utterance-level ASR that handles single utterances independently, the proposed method (which we call large-context end-to-end ASR) can explicitly utilize relationships between a current target utterance and all preceding utterances. The method is modeled by combining an attention-based encoder-decoder model, which is one of the most representative end-to-end ASR models, with hierarchical recurrent encoder-decoder models, which are effective language models for capturing long-range sequential contexts beyond the utterance boundaries. Experiments on Japanese discourse speech tasks demonstrate the proposed method yields significant ASR performance improvements compared with the conventional utterance-level end-to-end ASR system." @default.
- W2937649809 created "2019-04-25" @default.
- W2937649809 creator A5009756622 @default.
- W2937649809 creator A5060261786 @default.
- W2937649809 creator A5060644399 @default.
- W2937649809 creator A5067237053 @default.
- W2937649809 creator A5071828269 @default.
- W2937649809 creator A5087290011 @default.
- W2937649809 date "2019-05-01" @default.
- W2937649809 modified "2023-09-26" @default.
- W2937649809 title "Large Context End-to-end Automatic Speech Recognition via Extension of Hierarchical Recurrent Encoder-decoder Models" @default.
- W2937649809 cites W1902237438 @default.
- W2937649809 cites W1985258458 @default.
- W2937649809 cites W1993378086 @default.
- W2937649809 cites W2251849926 @default.
- W2937649809 cites W2327501763 @default.
- W2937649809 cites W2508661145 @default.
- W2937649809 cites W2521999726 @default.
- W2937649809 cites W2608712415 @default.
- W2937649809 cites W2786835190 @default.
- W2937649809 cites W2799800213 @default.
- W2937649809 cites W2889085040 @default.
- W2937649809 cites W2889374926 @default.
- W2937649809 cites W2962824709 @default.
- W2937649809 cites W2962893195 @default.
- W2937649809 cites W2963070863 @default.
- W2937649809 cites W2964093087 @default.
- W2937649809 cites W2964289193 @default.
- W2937649809 doi "https://doi.org/10.1109/icassp.2019.8683843" @default.
- W2937649809 hasPublicationYear "2019" @default.
- W2937649809 type Work @default.
- W2937649809 sameAs 2937649809 @default.
- W2937649809 citedByCount "21" @default.
- W2937649809 countsByYear W29376498092018 @default.
- W2937649809 countsByYear W29376498092019 @default.
- W2937649809 countsByYear W29376498092020 @default.
- W2937649809 countsByYear W29376498092021 @default.
- W2937649809 countsByYear W29376498092022 @default.
- W2937649809 crossrefType "proceedings-article" @default.
- W2937649809 hasAuthorship W2937649809A5009756622 @default.
- W2937649809 hasAuthorship W2937649809A5060261786 @default.
- W2937649809 hasAuthorship W2937649809A5060644399 @default.
- W2937649809 hasAuthorship W2937649809A5067237053 @default.
- W2937649809 hasAuthorship W2937649809A5071828269 @default.
- W2937649809 hasAuthorship W2937649809A5087290011 @default.
- W2937649809 hasConcept C111919701 @default.
- W2937649809 hasConcept C118505674 @default.
- W2937649809 hasConcept C120665830 @default.
- W2937649809 hasConcept C121332964 @default.
- W2937649809 hasConcept C137293760 @default.
- W2937649809 hasConcept C151730666 @default.
- W2937649809 hasConcept C154945302 @default.
- W2937649809 hasConcept C192209626 @default.
- W2937649809 hasConcept C204321447 @default.
- W2937649809 hasConcept C2775852435 @default.
- W2937649809 hasConcept C2779343474 @default.
- W2937649809 hasConcept C28490314 @default.
- W2937649809 hasConcept C41008148 @default.
- W2937649809 hasConcept C74296488 @default.
- W2937649809 hasConcept C86803240 @default.
- W2937649809 hasConceptScore W2937649809C111919701 @default.
- W2937649809 hasConceptScore W2937649809C118505674 @default.
- W2937649809 hasConceptScore W2937649809C120665830 @default.
- W2937649809 hasConceptScore W2937649809C121332964 @default.
- W2937649809 hasConceptScore W2937649809C137293760 @default.
- W2937649809 hasConceptScore W2937649809C151730666 @default.
- W2937649809 hasConceptScore W2937649809C154945302 @default.
- W2937649809 hasConceptScore W2937649809C192209626 @default.
- W2937649809 hasConceptScore W2937649809C204321447 @default.
- W2937649809 hasConceptScore W2937649809C2775852435 @default.
- W2937649809 hasConceptScore W2937649809C2779343474 @default.
- W2937649809 hasConceptScore W2937649809C28490314 @default.
- W2937649809 hasConceptScore W2937649809C41008148 @default.
- W2937649809 hasConceptScore W2937649809C74296488 @default.
- W2937649809 hasConceptScore W2937649809C86803240 @default.
- W2937649809 hasLocation W29376498091 @default.
- W2937649809 hasOpenAccess W2937649809 @default.
- W2937649809 hasPrimaryLocation W29376498091 @default.
- W2937649809 hasRelatedWork W1571404427 @default.
- W2937649809 hasRelatedWork W1911976934 @default.
- W2937649809 hasRelatedWork W2765601599 @default.
- W2937649809 hasRelatedWork W2800921391 @default.
- W2937649809 hasRelatedWork W2937649809 @default.
- W2937649809 hasRelatedWork W2973122799 @default.
- W2937649809 hasRelatedWork W2998814410 @default.
- W2937649809 hasRelatedWork W3107474891 @default.
- W2937649809 hasRelatedWork W4287905975 @default.
- W2937649809 hasRelatedWork W2613333037 @default.
- W2937649809 isParatext "false" @default.
- W2937649809 isRetracted "false" @default.
- W2937649809 magId "2937649809" @default.
- W2937649809 workType "article" @default.