Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950948614> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2950948614 abstract "Sequence-to-sequence models have shown success in end-to-end speech recognition. However these models have only used shallow acoustic encoder networks. In our work, we successively train very deep convolutional networks to add more expressive power and better generalization for end-to-end ASR models. We apply network-in-network principles, batch normalization, residual connections and convolutional LSTMs to build very deep recurrent and convolutional structures. Our models exploit the spectral structure in the feature space and add computational depth without overfitting issues. We experiment with the WSJ ASR task and achieve 10.5% word error rate without any dictionary or language using a 15 layer deep network." @default.
- W2950948614 created "2019-06-27" @default.
- W2950948614 creator A5016918393 @default.
- W2950948614 creator A5031967550 @default.
- W2950948614 creator A5075131520 @default.
- W2950948614 date "2016-10-10" @default.
- W2950948614 modified "2023-10-17" @default.
- W2950948614 title "Very Deep Convolutional Networks for End-to-End Speech Recognition" @default.
- W2950948614 cites W1828163288 @default.
- W2950948614 cites W2064675550 @default.
- W2950948614 cites W2097117768 @default.
- W2950948614 cites W2102113734 @default.
- W2950948614 cites W2108677974 @default.
- W2950948614 cites W2112796928 @default.
- W2950948614 cites W2125838338 @default.
- W2950948614 cites W2160815625 @default.
- W2950948614 cites W2198724430 @default.
- W2950948614 cites W2327501763 @default.
- W2950948614 cites W2949117887 @default.
- W2950948614 cites W2950621961 @default.
- W2950948614 cites W2953022181 @default.
- W2950948614 cites W2962826786 @default.
- W2950948614 cites W2962835968 @default.
- W2950948614 cites W2962965465 @default.
- W2950948614 cites W2964084166 @default.
- W2950948614 cites W2964121744 @default.
- W2950948614 cites W2964308564 @default.
- W2950948614 doi "https://doi.org/10.48550/arxiv.1610.03022" @default.
- W2950948614 hasPublicationYear "2016" @default.
- W2950948614 type Work @default.
- W2950948614 sameAs 2950948614 @default.
- W2950948614 citedByCount "10" @default.
- W2950948614 countsByYear W29509486142016 @default.
- W2950948614 countsByYear W29509486142017 @default.
- W2950948614 countsByYear W29509486142018 @default.
- W2950948614 countsByYear W29509486142020 @default.
- W2950948614 crossrefType "posted-content" @default.
- W2950948614 hasAuthorship W2950948614A5016918393 @default.
- W2950948614 hasAuthorship W2950948614A5031967550 @default.
- W2950948614 hasAuthorship W2950948614A5075131520 @default.
- W2950948614 hasBestOaLocation W29509486141 @default.
- W2950948614 hasConcept C101738243 @default.
- W2950948614 hasConcept C108583219 @default.
- W2950948614 hasConcept C111919701 @default.
- W2950948614 hasConcept C11413529 @default.
- W2950948614 hasConcept C118505674 @default.
- W2950948614 hasConcept C136886441 @default.
- W2950948614 hasConcept C144024400 @default.
- W2950948614 hasConcept C154945302 @default.
- W2950948614 hasConcept C155512373 @default.
- W2950948614 hasConcept C19165224 @default.
- W2950948614 hasConcept C22019652 @default.
- W2950948614 hasConcept C28490314 @default.
- W2950948614 hasConcept C40969351 @default.
- W2950948614 hasConcept C41008148 @default.
- W2950948614 hasConcept C50644808 @default.
- W2950948614 hasConcept C74296488 @default.
- W2950948614 hasConcept C81363708 @default.
- W2950948614 hasConceptScore W2950948614C101738243 @default.
- W2950948614 hasConceptScore W2950948614C108583219 @default.
- W2950948614 hasConceptScore W2950948614C111919701 @default.
- W2950948614 hasConceptScore W2950948614C11413529 @default.
- W2950948614 hasConceptScore W2950948614C118505674 @default.
- W2950948614 hasConceptScore W2950948614C136886441 @default.
- W2950948614 hasConceptScore W2950948614C144024400 @default.
- W2950948614 hasConceptScore W2950948614C154945302 @default.
- W2950948614 hasConceptScore W2950948614C155512373 @default.
- W2950948614 hasConceptScore W2950948614C19165224 @default.
- W2950948614 hasConceptScore W2950948614C22019652 @default.
- W2950948614 hasConceptScore W2950948614C28490314 @default.
- W2950948614 hasConceptScore W2950948614C40969351 @default.
- W2950948614 hasConceptScore W2950948614C41008148 @default.
- W2950948614 hasConceptScore W2950948614C50644808 @default.
- W2950948614 hasConceptScore W2950948614C74296488 @default.
- W2950948614 hasConceptScore W2950948614C81363708 @default.
- W2950948614 hasLocation W29509486141 @default.
- W2950948614 hasOpenAccess W2950948614 @default.
- W2950948614 hasPrimaryLocation W29509486141 @default.
- W2950948614 hasRelatedWork W2417429787 @default.
- W2950948614 hasRelatedWork W2563602643 @default.
- W2950948614 hasRelatedWork W2732415564 @default.
- W2950948614 hasRelatedWork W2997709384 @default.
- W2950948614 hasRelatedWork W3121671597 @default.
- W2950948614 hasRelatedWork W3162092403 @default.
- W2950948614 hasRelatedWork W4220996320 @default.
- W2950948614 hasRelatedWork W4283701629 @default.
- W2950948614 hasRelatedWork W4306194456 @default.
- W2950948614 hasRelatedWork W4309224979 @default.
- W2950948614 isParatext "false" @default.
- W2950948614 isRetracted "false" @default.
- W2950948614 magId "2950948614" @default.
- W2950948614 workType "article" @default.