Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319862425> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4319862425 abstract "There is growing interest in unifying the streaming and full-context automatic speech recognition (ASR) networks into a single end-to-end ASR model to simplify the model training and deployment for both use cases. While in real-world ASR applications, the streaming ASR models typically operate under more storage and computational constraints - e.g., on embedded devices - than any server-side full-context models. Motivated by the recent progress in Omni-sparsity supernet training, where multiple subnetworks are jointly optimized in one single model, this work aims to jointly learn a compact sparse on-device streaming ASR model, and a large dense server non-streaming model, in a single supernet. Next, we present that, performing supernet training on both wav2vec 2.0 self-supervised learning and supervised ASR fine-tuning can not only substantially improve the large non-streaming model as shown in prior works, and also be able to improve the compact sparse streaming model." @default.
- W4319862425 created "2023-02-11" @default.
- W4319862425 creator A5047358828 @default.
- W4319862425 creator A5066166549 @default.
- W4319862425 creator A5069296252 @default.
- W4319862425 creator A5069376593 @default.
- W4319862425 creator A5085953379 @default.
- W4319862425 creator A5039488725 @default.
- W4319862425 date "2023-01-09" @default.
- W4319862425 modified "2023-10-16" @default.
- W4319862425 title "Learning a Dual-Mode Speech Recognition Model VIA Self-Pruning" @default.
- W4319862425 cites W1494198834 @default.
- W4319862425 cites W2138019504 @default.
- W4319862425 cites W2407080277 @default.
- W4319862425 cites W2933138175 @default.
- W4319862425 cites W2963250244 @default.
- W4319862425 cites W2963925437 @default.
- W4319862425 cites W2981857663 @default.
- W4319862425 cites W2995181338 @default.
- W4319862425 cites W3008898571 @default.
- W4319862425 cites W3015194534 @default.
- W4319862425 cites W3016010032 @default.
- W4319862425 cites W3095311338 @default.
- W4319862425 cites W3097777922 @default.
- W4319862425 cites W3144557079 @default.
- W4319862425 cites W3146505093 @default.
- W4319862425 cites W3160766462 @default.
- W4319862425 cites W3161873870 @default.
- W4319862425 cites W3162309234 @default.
- W4319862425 cites W3162665866 @default.
- W4319862425 cites W3163203022 @default.
- W4319862425 cites W3196835955 @default.
- W4319862425 cites W3197478142 @default.
- W4319862425 cites W3198492054 @default.
- W4319862425 cites W3207326706 @default.
- W4319862425 cites W3207629995 @default.
- W4319862425 cites W4296068782 @default.
- W4319862425 doi "https://doi.org/10.1109/slt54892.2023.10022446" @default.
- W4319862425 hasPublicationYear "2023" @default.
- W4319862425 type Work @default.
- W4319862425 citedByCount "1" @default.
- W4319862425 crossrefType "proceedings-article" @default.
- W4319862425 hasAuthorship W4319862425A5039488725 @default.
- W4319862425 hasAuthorship W4319862425A5047358828 @default.
- W4319862425 hasAuthorship W4319862425A5066166549 @default.
- W4319862425 hasAuthorship W4319862425A5069296252 @default.
- W4319862425 hasAuthorship W4319862425A5069376593 @default.
- W4319862425 hasAuthorship W4319862425A5085953379 @default.
- W4319862425 hasBestOaLocation W43198624252 @default.
- W4319862425 hasConcept C105339364 @default.
- W4319862425 hasConcept C108010975 @default.
- W4319862425 hasConcept C111919701 @default.
- W4319862425 hasConcept C119857082 @default.
- W4319862425 hasConcept C124952713 @default.
- W4319862425 hasConcept C137293760 @default.
- W4319862425 hasConcept C142362112 @default.
- W4319862425 hasConcept C151730666 @default.
- W4319862425 hasConcept C154945302 @default.
- W4319862425 hasConcept C2779343474 @default.
- W4319862425 hasConcept C2780980858 @default.
- W4319862425 hasConcept C28490314 @default.
- W4319862425 hasConcept C41008148 @default.
- W4319862425 hasConcept C6557445 @default.
- W4319862425 hasConcept C86803240 @default.
- W4319862425 hasConceptScore W4319862425C105339364 @default.
- W4319862425 hasConceptScore W4319862425C108010975 @default.
- W4319862425 hasConceptScore W4319862425C111919701 @default.
- W4319862425 hasConceptScore W4319862425C119857082 @default.
- W4319862425 hasConceptScore W4319862425C124952713 @default.
- W4319862425 hasConceptScore W4319862425C137293760 @default.
- W4319862425 hasConceptScore W4319862425C142362112 @default.
- W4319862425 hasConceptScore W4319862425C151730666 @default.
- W4319862425 hasConceptScore W4319862425C154945302 @default.
- W4319862425 hasConceptScore W4319862425C2779343474 @default.
- W4319862425 hasConceptScore W4319862425C2780980858 @default.
- W4319862425 hasConceptScore W4319862425C28490314 @default.
- W4319862425 hasConceptScore W4319862425C41008148 @default.
- W4319862425 hasConceptScore W4319862425C6557445 @default.
- W4319862425 hasConceptScore W4319862425C86803240 @default.
- W4319862425 hasLocation W43198624251 @default.
- W4319862425 hasLocation W43198624252 @default.
- W4319862425 hasOpenAccess W4319862425 @default.
- W4319862425 hasPrimaryLocation W43198624251 @default.
- W4319862425 hasRelatedWork W1607147593 @default.
- W4319862425 hasRelatedWork W2369811061 @default.
- W4319862425 hasRelatedWork W2566006169 @default.
- W4319862425 hasRelatedWork W2770234245 @default.
- W4319862425 hasRelatedWork W2987774938 @default.
- W4319862425 hasRelatedWork W3089997100 @default.
- W4319862425 hasRelatedWork W4229499248 @default.
- W4319862425 hasRelatedWork W4378874356 @default.
- W4319862425 hasRelatedWork W620798607 @default.
- W4319862425 hasRelatedWork W632915154 @default.
- W4319862425 isParatext "false" @default.
- W4319862425 isRetracted "false" @default.
- W4319862425 workType "article" @default.