Matches in SemOpenAlex for { <https://semopenalex.org/work/W2938348542> ?p ?o ?g. }
Showing items 1 to 61 of
61
with 100 items per page.
- W2938348542 abstract "In this paper, we experiment with the recently introduced subword regularization technique [1] in the context of end-to-end automatic speech recognition (ASR). We present results from both attention-based and CTC-based ASR systems on two common benchmark datasets, the 80 hour Wall Street Journal corpus and 1,000 hour Librispeech corpus. We also introduce a novel subword beam search decoding algorithm that significantly improves the final performance of the CTC-based systems. Overall, we find that subword regularization improves the performance of both types of ASR systems, with the regularized attention-based model performing best overall." @default.
- W2938348542 created "2019-04-25" @default.
- W2938348542 creator A5039081803 @default.
- W2938348542 creator A5047280966 @default.
- W2938348542 date "2019-05-01" @default.
- W2938348542 modified "2023-09-25" @default.
- W2938348542 title "Subword Regularization and Beam Search Decoding for End-to-end Automatic Speech Recognition" @default.
- W2938348542 cites W1539673959 @default.
- W2938348542 cites W1865731626 @default.
- W2938348542 cites W2127141656 @default.
- W2938348542 cites W2144499799 @default.
- W2938348542 cites W2327501763 @default.
- W2938348542 cites W2799800213 @default.
- W2938348542 cites W2962784628 @default.
- W2938348542 cites W2962824709 @default.
- W2938348542 cites W2962826786 @default.
- W2938348542 cites W2963194026 @default.
- W2938348542 cites W2963979492 @default.
- W2938348542 doi "https://doi.org/10.1109/icassp.2019.8683531" @default.
- W2938348542 hasPublicationYear "2019" @default.
- W2938348542 type Work @default.
- W2938348542 sameAs 2938348542 @default.
- W2938348542 citedByCount "19" @default.
- W2938348542 countsByYear W29383485422020 @default.
- W2938348542 countsByYear W29383485422021 @default.
- W2938348542 countsByYear W29383485422022 @default.
- W2938348542 countsByYear W29383485422023 @default.
- W2938348542 crossrefType "proceedings-article" @default.
- W2938348542 hasAuthorship W2938348542A5039081803 @default.
- W2938348542 hasAuthorship W2938348542A5047280966 @default.
- W2938348542 hasConcept C11413529 @default.
- W2938348542 hasConcept C154945302 @default.
- W2938348542 hasConcept C2776135515 @default.
- W2938348542 hasConcept C28490314 @default.
- W2938348542 hasConcept C41008148 @default.
- W2938348542 hasConcept C57273362 @default.
- W2938348542 hasConcept C74296488 @default.
- W2938348542 hasConceptScore W2938348542C11413529 @default.
- W2938348542 hasConceptScore W2938348542C154945302 @default.
- W2938348542 hasConceptScore W2938348542C2776135515 @default.
- W2938348542 hasConceptScore W2938348542C28490314 @default.
- W2938348542 hasConceptScore W2938348542C41008148 @default.
- W2938348542 hasConceptScore W2938348542C57273362 @default.
- W2938348542 hasConceptScore W2938348542C74296488 @default.
- W2938348542 hasLocation W29383485421 @default.
- W2938348542 hasOpenAccess W2938348542 @default.
- W2938348542 hasPrimaryLocation W29383485421 @default.
- W2938348542 hasRelatedWork W2351992004 @default.
- W2938348542 hasRelatedWork W2358034992 @default.
- W2938348542 hasRelatedWork W2367936931 @default.
- W2938348542 hasRelatedWork W2380207131 @default.
- W2938348542 hasRelatedWork W2938348542 @default.
- W2938348542 hasRelatedWork W2976556660 @default.
- W2938348542 hasRelatedWork W2996122240 @default.
- W2938348542 hasRelatedWork W3156915121 @default.
- W2938348542 hasRelatedWork W3197898596 @default.
- W2938348542 hasRelatedWork W4285757700 @default.
- W2938348542 isParatext "false" @default.
- W2938348542 isRetracted "false" @default.
- W2938348542 magId "2938348542" @default.
- W2938348542 workType "article" @default.