FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3216100938> ?p ?o ?g. }

• W3216100938 endingPage "2208" @default.
• W3216100938 startingPage "2195" @default.
• W3216100938 abstract "Real-time machine speech translation systems mimic human interpreters and translate incoming speech from a source language to the target language in real-time. Such systems can be achieved by performing low-latency processing in ASR (automatic speech recognition) module before passing the output to MT (machine translation) and TTS (text-to-speech synthesis) modules. Although several studies recently proposed sequence mechanisms for neural incremental ASR (ISR), these frameworks have a more complicated training mechanism than the standard attention-based ASR because they have to decide the incremental step and learn the alignment between speech and text. In this paper, we propose attention-transfer ISR (AT-ISR) that learns the knowledge from attention-based non-incremental ASR for a low delay end-to-end speech recognition. ISR comes with a trade-off between delay and performance, so we investigate how to reduce AT-ISR delay without a significant performance drop. Our experiment shows that AT-ISR achieves a comparable performance to the non-incremental ASR when the incremental recognition begins after the speech utterance reaches 25% of the complete utterance length. Additional experiments to investigate the effect of ISR on translation tasks are also performed. The focus is to find the optimum granularity of the output unit. The results reveal that our end-to-end subword-level ISR resulted in the best translation quality with the lowest WER and the lowest uncovered-word rate." @default.
• W3216100938 created "2021-12-06" @default.
• W3216100938 creator A5020994673 @default.
• W3216100938 creator A5040108974 @default.
• W3216100938 creator A5048192694 @default.
• W3216100938 date "2021-12-01" @default.
• W3216100938 modified "2023-09-23" @default.
• W3216100938 title "Neural Incremental Speech Recognition Toward Real-Time Machine Speech Translation" @default.
• W3216100938 cites W121610373 @default.
• W3216100938 cites W1524333225 @default.
• W3216100938 cites W1902237438 @default.
• W3216100938 cites W2002138135 @default.
• W3216100938 cites W2024490156 @default.
• W3216100938 cites W2078861931 @default.
• W3216100938 cites W2089629691 @default.
• W3216100938 cites W2101105183 @default.
• W3216100938 cites W2103584254 @default.
• W3216100938 cites W2123301721 @default.
• W3216100938 cites W2125838338 @default.
• W3216100938 cites W2142416747 @default.
• W3216100938 cites W2172126254 @default.
• W3216100938 cites W2250357346 @default.
• W3216100938 cites W2263232528 @default.
• W3216100938 cites W2327501763 @default.
• W3216100938 cites W2398009384 @default.
• W3216100938 cites W2517566275 @default.
• W3216100938 cites W2525778437 @default.
• W3216100938 cites W2526425061 @default.
• W3216100938 cites W2600628583 @default.
• W3216100938 cites W2747874407 @default.
• W3216100938 cites W2759128986 @default.
• W3216100938 cites W2805490244 @default.
• W3216100938 cites W2884852625 @default.
• W3216100938 cites W2890197052 @default.
• W3216100938 cites W2901607128 @default.
• W3216100938 cites W2962680099 @default.
• W3216100938 cites W2962742956 @default.
• W3216100938 cites W2962784628 @default.
• W3216100938 cites W2962824709 @default.
• W3216100938 cites W2963250244 @default.
• W3216100938 cites W2963382687 @default.
• W3216100938 cites W2963729263 @default.
• W3216100938 cites W2963979492 @default.
• W3216100938 cites W2964308564 @default.
• W3216100938 cites W2972356804 @default.
• W3216100938 cites W2972448360 @default.
• W3216100938 cites W3015194534 @default.
• W3216100938 cites W3015457435 @default.
• W3216100938 cites W3015654466 @default.
• W3216100938 cites W3015974384 @default.
• W3216100938 cites W3034586846 @default.
• W3216100938 cites W854541894 @default.
• W3216100938 cites W90894508 @default.
• W3216100938 doi "https://doi.org/10.1587/transinf.2021edp7014" @default.
• W3216100938 hasPublicationYear "2021" @default.
• W3216100938 type Work @default.
• W3216100938 sameAs 3216100938 @default.
• W3216100938 citedByCount "0" @default.
• W3216100938 crossrefType "journal-article" @default.
• W3216100938 hasAuthorship W3216100938A5020994673 @default.
• W3216100938 hasAuthorship W3216100938A5040108974 @default.
• W3216100938 hasAuthorship W3216100938A5048192694 @default.
• W3216100938 hasBestOaLocation W32161009381 @default.
• W3216100938 hasConcept C14999030 @default.
• W3216100938 hasConcept C154945302 @default.
• W3216100938 hasConcept C203005215 @default.
• W3216100938 hasConcept C204321447 @default.
• W3216100938 hasConcept C2775852435 @default.
• W3216100938 hasConcept C2780366754 @default.
• W3216100938 hasConcept C28490314 @default.
• W3216100938 hasConcept C40969351 @default.
• W3216100938 hasConcept C41008148 @default.
• W3216100938 hasConcept C76155785 @default.
• W3216100938 hasConcept C82876162 @default.
• W3216100938 hasConceptScore W3216100938C14999030 @default.
• W3216100938 hasConceptScore W3216100938C154945302 @default.
• W3216100938 hasConceptScore W3216100938C203005215 @default.
• W3216100938 hasConceptScore W3216100938C204321447 @default.
• W3216100938 hasConceptScore W3216100938C2775852435 @default.
• W3216100938 hasConceptScore W3216100938C2780366754 @default.
• W3216100938 hasConceptScore W3216100938C28490314 @default.
• W3216100938 hasConceptScore W3216100938C40969351 @default.
• W3216100938 hasConceptScore W3216100938C41008148 @default.
• W3216100938 hasConceptScore W3216100938C76155785 @default.
• W3216100938 hasConceptScore W3216100938C82876162 @default.
• W3216100938 hasIssue "12" @default.
• W3216100938 hasLocation W32161009381 @default.
• W3216100938 hasOpenAccess W3216100938 @default.
• W3216100938 hasPrimaryLocation W32161009381 @default.
• W3216100938 hasRelatedWork W1510746193 @default.
• W3216100938 hasRelatedWork W1556750318 @default.
• W3216100938 hasRelatedWork W1970987322 @default.
• W3216100938 hasRelatedWork W2066913438 @default.
• W3216100938 hasRelatedWork W2114483840 @default.
• W3216100938 hasRelatedWork W2405158679 @default.
• W3216100938 hasRelatedWork W3100608856 @default.
• W3216100938 hasRelatedWork W3107474891 @default.
• W3216100938 hasRelatedWork W3184351855 @default.

• next