Matches in SemOpenAlex for { <https://semopenalex.org/work/W2972981541> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2972981541 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.
- W2972981541 created "2019-09-19" @default.
- W2972981541 creator A5022894020 @default.
- W2972981541 creator A5028863551 @default.
- W2972981541 creator A5062740398 @default.
- W2972981541 creator A5076409146 @default.
- W2972981541 date "2019-09-15" @default.
- W2972981541 modified "2023-09-28" @default.
- W2972981541 title "Exploiting Semi-Supervised Training Through a Dropout Regularization in End-to-End Speech Recognition" @default.
- W2972981541 doi "https://doi.org/10.21437/interspeech.2019-3246" @default.
- W2972981541 hasPublicationYear "2019" @default.
- W2972981541 type Work @default.
- W2972981541 sameAs 2972981541 @default.
- W2972981541 citedByCount "9" @default.
- W2972981541 countsByYear W29729815412020 @default.
- W2972981541 countsByYear W29729815412021 @default.
- W2972981541 crossrefType "proceedings-article" @default.
- W2972981541 hasAuthorship W2972981541A5022894020 @default.
- W2972981541 hasAuthorship W2972981541A5028863551 @default.
- W2972981541 hasAuthorship W2972981541A5062740398 @default.
- W2972981541 hasAuthorship W2972981541A5076409146 @default.
- W2972981541 hasBestOaLocation W29729815412 @default.
- W2972981541 hasConcept C111919701 @default.
- W2972981541 hasConcept C119857082 @default.
- W2972981541 hasConcept C121332964 @default.
- W2972981541 hasConcept C154945302 @default.
- W2972981541 hasConcept C163258240 @default.
- W2972981541 hasConcept C2775852435 @default.
- W2972981541 hasConcept C2776135515 @default.
- W2972981541 hasConcept C2776145597 @default.
- W2972981541 hasConcept C28490314 @default.
- W2972981541 hasConcept C41008148 @default.
- W2972981541 hasConcept C43214815 @default.
- W2972981541 hasConcept C62520636 @default.
- W2972981541 hasConcept C74296488 @default.
- W2972981541 hasConcept C81917197 @default.
- W2972981541 hasConcept C98045186 @default.
- W2972981541 hasConceptScore W2972981541C111919701 @default.
- W2972981541 hasConceptScore W2972981541C119857082 @default.
- W2972981541 hasConceptScore W2972981541C121332964 @default.
- W2972981541 hasConceptScore W2972981541C154945302 @default.
- W2972981541 hasConceptScore W2972981541C163258240 @default.
- W2972981541 hasConceptScore W2972981541C2775852435 @default.
- W2972981541 hasConceptScore W2972981541C2776135515 @default.
- W2972981541 hasConceptScore W2972981541C2776145597 @default.
- W2972981541 hasConceptScore W2972981541C28490314 @default.
- W2972981541 hasConceptScore W2972981541C41008148 @default.
- W2972981541 hasConceptScore W2972981541C43214815 @default.
- W2972981541 hasConceptScore W2972981541C62520636 @default.
- W2972981541 hasConceptScore W2972981541C74296488 @default.
- W2972981541 hasConceptScore W2972981541C81917197 @default.
- W2972981541 hasConceptScore W2972981541C98045186 @default.
- W2972981541 hasLocation W29729815411 @default.
- W2972981541 hasLocation W29729815412 @default.
- W2972981541 hasOpenAccess W2972981541 @default.
- W2972981541 hasPrimaryLocation W29729815411 @default.
- W2972981541 hasRelatedWork W114932164 @default.
- W2972981541 hasRelatedWork W1495019370 @default.
- W2972981541 hasRelatedWork W2737108017 @default.
- W2972981541 hasRelatedWork W2749784707 @default.
- W2972981541 hasRelatedWork W2766572290 @default.
- W2972981541 hasRelatedWork W2776984718 @default.
- W2972981541 hasRelatedWork W2793863914 @default.
- W2972981541 hasRelatedWork W2803306015 @default.
- W2972981541 hasRelatedWork W2936774411 @default.
- W2972981541 hasRelatedWork W2949788262 @default.
- W2972981541 hasRelatedWork W2952010730 @default.
- W2972981541 hasRelatedWork W2967046144 @default.
- W2972981541 hasRelatedWork W2982608933 @default.
- W2972981541 hasRelatedWork W2992448548 @default.
- W2972981541 hasRelatedWork W3105804405 @default.
- W2972981541 hasRelatedWork W3109234242 @default.
- W2972981541 hasRelatedWork W3142629163 @default.
- W2972981541 hasRelatedWork W3156508770 @default.
- W2972981541 hasRelatedWork W3182245104 @default.
- W2972981541 hasRelatedWork W3208049241 @default.
- W2972981541 isParatext "false" @default.
- W2972981541 isRetracted "false" @default.
- W2972981541 magId "2972981541" @default.
- W2972981541 workType "article" @default.