Matches in SemOpenAlex for { <https://semopenalex.org/work/W3034311908> ?p ?o ?g. }
Showing items 1 to 76 of
76
with 100 items per page.
- W3034311908 endingPage "445" @default.
- W3034311908 startingPage "437" @default.
- W3034311908 abstract "Advanced neural network models have penetrated Automatic Speech Recognition (ASR) in recent years, however, in language modeling many systems still rely on traditional Back-off N-gram Language Models (BNLM) partly or entirely. The reason for this are the high cost and complexity of training and using neural language models, mostly possible by adding a second decoding pass (rescoring). In our recent work we have significantly improved the online performance of a conversational speech transcription system by transferring knowledge from a Recurrent Neural Network Language Model (RNNLM) to the single pass BNLM with text generation based data augmentation. In the present paper we analyze the amount of transferable knowledge and demonstrate that the neural augmented LM (RNN-BNLM) can help to capture almost 50% of the knowledge of the RNNLM yet by dropping the second decoding pass and making the system real-time capable. We also systematically compare word and subword LMs and show that subword-based neural text augmentation can be especially beneficial in under-resourced conditions. In addition, we show that using the RNN-BNLM in the first pass followed by a neural second pass, offline ASR results can be even significantly improved." @default.
- W3034311908 created "2020-06-19" @default.
- W3034311908 creator A5014608650 @default.
- W3034311908 creator A5020514527 @default.
- W3034311908 creator A5043901293 @default.
- W3034311908 creator A5075146981 @default.
- W3034311908 date "2020-01-01" @default.
- W3034311908 modified "2023-09-23" @default.
- W3034311908 title "On the Effectiveness of Neural Text Generation Based Data Augmentation for Recognition of Morphologically Rich Speech" @default.
- W3034311908 cites W1631260214 @default.
- W3034311908 cites W2042783153 @default.
- W3034311908 cites W2110415041 @default.
- W3034311908 cites W2117621558 @default.
- W3034311908 cites W2402268235 @default.
- W3034311908 cites W2714176837 @default.
- W3034311908 cites W2735949438 @default.
- W3034311908 cites W2888867175 @default.
- W3034311908 cites W2939021222 @default.
- W3034311908 cites W2943845043 @default.
- W3034311908 cites W2972551035 @default.
- W3034311908 cites W2977433292 @default.
- W3034311908 doi "https://doi.org/10.1007/978-3-030-58323-1_47" @default.
- W3034311908 hasPublicationYear "2020" @default.
- W3034311908 type Work @default.
- W3034311908 sameAs 3034311908 @default.
- W3034311908 citedByCount "0" @default.
- W3034311908 crossrefType "book-chapter" @default.
- W3034311908 hasAuthorship W3034311908A5014608650 @default.
- W3034311908 hasAuthorship W3034311908A5020514527 @default.
- W3034311908 hasAuthorship W3034311908A5043901293 @default.
- W3034311908 hasAuthorship W3034311908A5075146981 @default.
- W3034311908 hasBestOaLocation W30343119082 @default.
- W3034311908 hasConcept C11413529 @default.
- W3034311908 hasConcept C137293760 @default.
- W3034311908 hasConcept C138885662 @default.
- W3034311908 hasConcept C147168706 @default.
- W3034311908 hasConcept C154945302 @default.
- W3034311908 hasConcept C204321447 @default.
- W3034311908 hasConcept C28490314 @default.
- W3034311908 hasConcept C41008148 @default.
- W3034311908 hasConcept C41895202 @default.
- W3034311908 hasConcept C50644808 @default.
- W3034311908 hasConcept C57273362 @default.
- W3034311908 hasConcept C90805587 @default.
- W3034311908 hasConceptScore W3034311908C11413529 @default.
- W3034311908 hasConceptScore W3034311908C137293760 @default.
- W3034311908 hasConceptScore W3034311908C138885662 @default.
- W3034311908 hasConceptScore W3034311908C147168706 @default.
- W3034311908 hasConceptScore W3034311908C154945302 @default.
- W3034311908 hasConceptScore W3034311908C204321447 @default.
- W3034311908 hasConceptScore W3034311908C28490314 @default.
- W3034311908 hasConceptScore W3034311908C41008148 @default.
- W3034311908 hasConceptScore W3034311908C41895202 @default.
- W3034311908 hasConceptScore W3034311908C50644808 @default.
- W3034311908 hasConceptScore W3034311908C57273362 @default.
- W3034311908 hasConceptScore W3034311908C90805587 @default.
- W3034311908 hasLocation W30343119081 @default.
- W3034311908 hasLocation W30343119082 @default.
- W3034311908 hasOpenAccess W3034311908 @default.
- W3034311908 hasPrimaryLocation W30343119081 @default.
- W3034311908 hasRelatedWork W1508636238 @default.
- W3034311908 hasRelatedWork W2044223291 @default.
- W3034311908 hasRelatedWork W2115483262 @default.
- W3034311908 hasRelatedWork W2251771687 @default.
- W3034311908 hasRelatedWork W2747917286 @default.
- W3034311908 hasRelatedWork W2896411932 @default.
- W3034311908 hasRelatedWork W2996122240 @default.
- W3034311908 hasRelatedWork W3107474891 @default.
- W3034311908 hasRelatedWork W3151526698 @default.
- W3034311908 hasRelatedWork W3199016780 @default.
- W3034311908 isParatext "false" @default.
- W3034311908 isRetracted "false" @default.
- W3034311908 magId "3034311908" @default.
- W3034311908 workType "book-chapter" @default.