FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2894778092> ?p ?o ?g. }

• W2894778092 endingPage "510" @default.
• W2894778092 startingPage "500" @default.
• W2894778092 abstract "End-to-end neural networks have shown promising results on large vocabulary continuous speech recognition (LVCSR) systems. However, it is challenging to integrate domain knowledge into such systems. Specifically, articulatory features (AFs) which are inspired by the human speech production mechanism can help in speech recognition. This paper presents two approaches to incorporate domain knowledge into end-to-end training: (a) fine-tuning networks which reuse hidden layer representations of AF extractors as input for ASR tasks; (b) progressive networks which combine articulatory knowledge by lateral connections from AF extractors. We evaluate the proposed approaches on the speech Wall Street Journal corpus and test on the eval92 standard evaluation dataset. Results show that both fine-tuning and progressive networks can integrate articulatory information into end-to-end learning and outperform previous systems." @default.
• W2894778092 created "2018-10-12" @default.
• W2894778092 creator A5023714181 @default.
• W2894778092 creator A5033486668 @default.
• W2894778092 creator A5040807269 @default.
• W2894778092 creator A5045428440 @default.
• W2894778092 creator A5091406493 @default.
• W2894778092 date "2018-01-01" @default.
• W2894778092 modified "2023-10-06" @default.
• W2894778092 title "Combining Articulatory Features with End-to-End Learning in Speech Recognition" @default.
• W2894778092 cites W1533416326 @default.
• W2894778092 cites W1600744878 @default.
• W2894778092 cites W1977021391 @default.
• W2894778092 cites W1980850109 @default.
• W2894778092 cites W2024490156 @default.
• W2894778092 cites W2060630096 @default.
• W2894778092 cites W2112796928 @default.
• W2894778092 cites W2124558353 @default.
• W2894778092 cites W2127141656 @default.
• W2894778092 cites W2140372979 @default.
• W2894778092 cites W2148154194 @default.
• W2894778092 cites W2151311453 @default.
• W2894778092 cites W2155273149 @default.
• W2894778092 cites W2164931619 @default.
• W2894778092 cites W2327501763 @default.
• W2894778092 cites W2521999726 @default.
• W2894778092 cites W2766058732 @default.
• W2894778092 cites W29056978 @default.
• W2894778092 cites W2962826786 @default.
• W2894778092 doi "https://doi.org/10.1007/978-3-030-01424-7_49" @default.
• W2894778092 hasPublicationYear "2018" @default.
• W2894778092 type Work @default.
• W2894778092 sameAs 2894778092 @default.
• W2894778092 citedByCount "2" @default.
• W2894778092 countsByYear W28947780922019 @default.
• W2894778092 countsByYear W28947780922020 @default.
• W2894778092 crossrefType "book-chapter" @default.
• W2894778092 hasAuthorship W2894778092A5023714181 @default.
• W2894778092 hasAuthorship W2894778092A5033486668 @default.
• W2894778092 hasAuthorship W2894778092A5040807269 @default.
• W2894778092 hasAuthorship W2894778092A5045428440 @default.
• W2894778092 hasAuthorship W2894778092A5091406493 @default.
• W2894778092 hasConcept C134306372 @default.
• W2894778092 hasConcept C138885662 @default.
• W2894778092 hasConcept C154945302 @default.
• W2894778092 hasConcept C18903297 @default.
• W2894778092 hasConcept C206588197 @default.
• W2894778092 hasConcept C207685749 @default.
• W2894778092 hasConcept C2777601683 @default.
• W2894778092 hasConcept C28490314 @default.
• W2894778092 hasConcept C33923547 @default.
• W2894778092 hasConcept C36503486 @default.
• W2894778092 hasConcept C41008148 @default.
• W2894778092 hasConcept C41895202 @default.
• W2894778092 hasConcept C43617652 @default.
• W2894778092 hasConcept C50644808 @default.
• W2894778092 hasConcept C74296488 @default.
• W2894778092 hasConcept C86803240 @default.
• W2894778092 hasConceptScore W2894778092C134306372 @default.
• W2894778092 hasConceptScore W2894778092C138885662 @default.
• W2894778092 hasConceptScore W2894778092C154945302 @default.
• W2894778092 hasConceptScore W2894778092C18903297 @default.
• W2894778092 hasConceptScore W2894778092C206588197 @default.
• W2894778092 hasConceptScore W2894778092C207685749 @default.
• W2894778092 hasConceptScore W2894778092C2777601683 @default.
• W2894778092 hasConceptScore W2894778092C28490314 @default.
• W2894778092 hasConceptScore W2894778092C33923547 @default.
• W2894778092 hasConceptScore W2894778092C36503486 @default.
• W2894778092 hasConceptScore W2894778092C41008148 @default.
• W2894778092 hasConceptScore W2894778092C41895202 @default.
• W2894778092 hasConceptScore W2894778092C43617652 @default.
• W2894778092 hasConceptScore W2894778092C50644808 @default.
• W2894778092 hasConceptScore W2894778092C74296488 @default.
• W2894778092 hasConceptScore W2894778092C86803240 @default.
• W2894778092 hasLocation W28947780921 @default.
• W2894778092 hasOpenAccess W2894778092 @default.
• W2894778092 hasPrimaryLocation W28947780921 @default.
• W2894778092 hasRelatedWork W1993660824 @default.
• W2894778092 hasRelatedWork W2059314128 @default.
• W2894778092 hasRelatedWork W2062652351 @default.
• W2894778092 hasRelatedWork W2127846433 @default.
• W2894778092 hasRelatedWork W2172236910 @default.
• W2894778092 hasRelatedWork W2547793174 @default.
• W2894778092 hasRelatedWork W2613090068 @default.
• W2894778092 hasRelatedWork W2770107007 @default.
• W2894778092 hasRelatedWork W2888131732 @default.
• W2894778092 hasRelatedWork W2890244912 @default.
• W2894778092 hasRelatedWork W2912937645 @default.
• W2894778092 hasRelatedWork W2913851961 @default.
• W2894778092 hasRelatedWork W2919123506 @default.
• W2894778092 hasRelatedWork W2944177268 @default.
• W2894778092 hasRelatedWork W2963812242 @default.
• W2894778092 hasRelatedWork W2971766686 @default.
• W2894778092 hasRelatedWork W2972808286 @default.
• W2894778092 hasRelatedWork W3009565979 @default.
• W2894778092 hasRelatedWork W3011926625 @default.
• W2894778092 hasRelatedWork W3048912752 @default.
• W2894778092 isParatext "false" @default.

• next