Matches in SemOpenAlex for { <https://semopenalex.org/work/W2967046144> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W2967046144 abstract "In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework. The first step in our approach involves training a seed model on the limited amount of labelled data. Additional unlabelled speech data is employed through a data selection mechanism to obtain the best hypothesized output, further used to retrain the seed model. However, uncertainties of the model may not be well captured with a single hypothesis. As opposed to this technique, we apply a dropout mechanism to capture the uncertainty by obtaining multiple hypothesized text transcripts of an speech recording. We assume that the diversity of automatically generated transcripts for an utterance will implicitly increase the reliability of the model. Finally, the data selection process is also applied on these hypothesized transcripts to reduce the uncertainty. Experiments on freely available TEDLIUM corpus and proprietary Adobe's internal dataset show that the proposed approach significantly reduces ASR errors, compared to the baseline model." @default.
- W2967046144 created "2019-08-22" @default.
- W2967046144 creator A5022894020 @default.
- W2967046144 creator A5028863551 @default.
- W2967046144 creator A5062740398 @default.
- W2967046144 creator A5076409146 @default.
- W2967046144 date "2019-08-08" @default.
- W2967046144 modified "2023-09-27" @default.
- W2967046144 title "Exploiting semi-supervised training through a dropout regularization in end-to-end speech recognition" @default.
- W2967046144 cites W1494198834 @default.
- W2967046144 cites W1524333225 @default.
- W2967046144 cites W1892788530 @default.
- W2967046144 cites W2091432990 @default.
- W2967046144 cites W2095705004 @default.
- W2967046144 cites W2184045248 @default.
- W2967046144 cites W2250357346 @default.
- W2967046144 cites W2526425061 @default.
- W2967046144 cites W2617565145 @default.
- W2967046144 cites W2886180730 @default.
- W2967046144 cites W2889213362 @default.
- W2967046144 cites W2939216642 @default.
- W2967046144 cites W2962780374 @default.
- W2967046144 cites W2963211739 @default.
- W2967046144 cites W2964059111 @default.
- W2967046144 hasPublicationYear "2019" @default.
- W2967046144 type Work @default.
- W2967046144 sameAs 2967046144 @default.
- W2967046144 citedByCount "0" @default.
- W2967046144 crossrefType "posted-content" @default.
- W2967046144 hasAuthorship W2967046144A5022894020 @default.
- W2967046144 hasAuthorship W2967046144A5028863551 @default.
- W2967046144 hasAuthorship W2967046144A5062740398 @default.
- W2967046144 hasAuthorship W2967046144A5076409146 @default.
- W2967046144 hasConcept C111368507 @default.
- W2967046144 hasConcept C111919701 @default.
- W2967046144 hasConcept C119857082 @default.
- W2967046144 hasConcept C121332964 @default.
- W2967046144 hasConcept C12725497 @default.
- W2967046144 hasConcept C127313418 @default.
- W2967046144 hasConcept C154945302 @default.
- W2967046144 hasConcept C163258240 @default.
- W2967046144 hasConcept C2775852435 @default.
- W2967046144 hasConcept C2776135515 @default.
- W2967046144 hasConcept C2776145597 @default.
- W2967046144 hasConcept C28490314 @default.
- W2967046144 hasConcept C41008148 @default.
- W2967046144 hasConcept C43214815 @default.
- W2967046144 hasConcept C62520636 @default.
- W2967046144 hasConcept C74296488 @default.
- W2967046144 hasConcept C81917197 @default.
- W2967046144 hasConcept C98045186 @default.
- W2967046144 hasConceptScore W2967046144C111368507 @default.
- W2967046144 hasConceptScore W2967046144C111919701 @default.
- W2967046144 hasConceptScore W2967046144C119857082 @default.
- W2967046144 hasConceptScore W2967046144C121332964 @default.
- W2967046144 hasConceptScore W2967046144C12725497 @default.
- W2967046144 hasConceptScore W2967046144C127313418 @default.
- W2967046144 hasConceptScore W2967046144C154945302 @default.
- W2967046144 hasConceptScore W2967046144C163258240 @default.
- W2967046144 hasConceptScore W2967046144C2775852435 @default.
- W2967046144 hasConceptScore W2967046144C2776135515 @default.
- W2967046144 hasConceptScore W2967046144C2776145597 @default.
- W2967046144 hasConceptScore W2967046144C28490314 @default.
- W2967046144 hasConceptScore W2967046144C41008148 @default.
- W2967046144 hasConceptScore W2967046144C43214815 @default.
- W2967046144 hasConceptScore W2967046144C62520636 @default.
- W2967046144 hasConceptScore W2967046144C74296488 @default.
- W2967046144 hasConceptScore W2967046144C81917197 @default.
- W2967046144 hasConceptScore W2967046144C98045186 @default.
- W2967046144 hasLocation W29670461441 @default.
- W2967046144 hasOpenAccess W2967046144 @default.
- W2967046144 hasPrimaryLocation W29670461441 @default.
- W2967046144 hasRelatedWork W114932164 @default.
- W2967046144 hasRelatedWork W1495019370 @default.
- W2967046144 hasRelatedWork W2737108017 @default.
- W2967046144 hasRelatedWork W2749784707 @default.
- W2967046144 hasRelatedWork W2766572290 @default.
- W2967046144 hasRelatedWork W2776984718 @default.
- W2967046144 hasRelatedWork W2793863914 @default.
- W2967046144 hasRelatedWork W2803306015 @default.
- W2967046144 hasRelatedWork W2949788262 @default.
- W2967046144 hasRelatedWork W2972981541 @default.
- W2967046144 hasRelatedWork W3082082599 @default.
- W2967046144 hasRelatedWork W3105804405 @default.
- W2967046144 hasRelatedWork W3109234242 @default.
- W2967046144 hasRelatedWork W3142629163 @default.
- W2967046144 hasRelatedWork W3150519376 @default.
- W2967046144 hasRelatedWork W3156508770 @default.
- W2967046144 hasRelatedWork W3162334527 @default.
- W2967046144 hasRelatedWork W3182245104 @default.
- W2967046144 hasRelatedWork W3205181379 @default.
- W2967046144 hasRelatedWork W3208049241 @default.
- W2967046144 isParatext "false" @default.
- W2967046144 isRetracted "false" @default.
- W2967046144 magId "2967046144" @default.
- W2967046144 workType "article" @default.