Matches in SemOpenAlex for { <https://semopenalex.org/work/W2852420917> ?p ?o ?g. }
Showing items 1 to 94 of
94
with 100 items per page.
- W2852420917 abstract "This paper presents the effects of transfer learning on deep neural network based speech recognition systems. The source acoustic model is trained on a large corpus of call centers telephony records, and an acoustically mismatched out-of-domain data that consists of the meeting recordings of the Grand National Assembly of Turkey is selected as the target. Our goal is to adapt the source model to the target data using transfer learning, and we investigate the effects of different target training data sizes, transferred layer counts and feature extractors on transfer learning. Our experiments show that for all target training sizes, the transferred models outperformed the models that are only trained on the target data, and the model that is transferred using 20 hours of target data achieved 7.8% higher recognition accuracy than the source model." @default.
- W2852420917 created "2018-07-19" @default.
- W2852420917 creator A5008979592 @default.
- W2852420917 creator A5017246112 @default.
- W2852420917 creator A5038667215 @default.
- W2852420917 creator A5050368406 @default.
- W2852420917 date "2018-05-01" @default.
- W2852420917 modified "2023-09-28" @default.
- W2852420917 title "Transfer learning for automatic speech recognition systems" @default.
- W2852420917 cites W1978660892 @default.
- W2852420917 cites W2137844145 @default.
- W2852420917 cites W2160815625 @default.
- W2852420917 cites W2165698076 @default.
- W2852420917 cites W2169362066 @default.
- W2852420917 cites W2295582178 @default.
- W2852420917 cites W2346660049 @default.
- W2852420917 cites W2963303951 @default.
- W2852420917 doi "https://doi.org/10.1109/siu.2018.8404628" @default.
- W2852420917 hasPublicationYear "2018" @default.
- W2852420917 type Work @default.
- W2852420917 sameAs 2852420917 @default.
- W2852420917 citedByCount "3" @default.
- W2852420917 countsByYear W28524209172020 @default.
- W2852420917 countsByYear W28524209172023 @default.
- W2852420917 crossrefType "proceedings-article" @default.
- W2852420917 hasAuthorship W2852420917A5008979592 @default.
- W2852420917 hasAuthorship W2852420917A5017246112 @default.
- W2852420917 hasAuthorship W2852420917A5038667215 @default.
- W2852420917 hasAuthorship W2852420917A5050368406 @default.
- W2852420917 hasConcept C108583219 @default.
- W2852420917 hasConcept C119857082 @default.
- W2852420917 hasConcept C134306372 @default.
- W2852420917 hasConcept C138885662 @default.
- W2852420917 hasConcept C150899416 @default.
- W2852420917 hasConcept C153180895 @default.
- W2852420917 hasConcept C154945302 @default.
- W2852420917 hasConcept C155635449 @default.
- W2852420917 hasConcept C173608175 @default.
- W2852420917 hasConcept C195358072 @default.
- W2852420917 hasConcept C2776145971 @default.
- W2852420917 hasConcept C2776175482 @default.
- W2852420917 hasConcept C2776401178 @default.
- W2852420917 hasConcept C28490314 @default.
- W2852420917 hasConcept C33923547 @default.
- W2852420917 hasConcept C36503486 @default.
- W2852420917 hasConcept C41008148 @default.
- W2852420917 hasConcept C41895202 @default.
- W2852420917 hasConcept C50644808 @default.
- W2852420917 hasConcept C51632099 @default.
- W2852420917 hasConcept C61328038 @default.
- W2852420917 hasConcept C67186912 @default.
- W2852420917 hasConcept C76155785 @default.
- W2852420917 hasConcept C77088390 @default.
- W2852420917 hasConceptScore W2852420917C108583219 @default.
- W2852420917 hasConceptScore W2852420917C119857082 @default.
- W2852420917 hasConceptScore W2852420917C134306372 @default.
- W2852420917 hasConceptScore W2852420917C138885662 @default.
- W2852420917 hasConceptScore W2852420917C150899416 @default.
- W2852420917 hasConceptScore W2852420917C153180895 @default.
- W2852420917 hasConceptScore W2852420917C154945302 @default.
- W2852420917 hasConceptScore W2852420917C155635449 @default.
- W2852420917 hasConceptScore W2852420917C173608175 @default.
- W2852420917 hasConceptScore W2852420917C195358072 @default.
- W2852420917 hasConceptScore W2852420917C2776145971 @default.
- W2852420917 hasConceptScore W2852420917C2776175482 @default.
- W2852420917 hasConceptScore W2852420917C2776401178 @default.
- W2852420917 hasConceptScore W2852420917C28490314 @default.
- W2852420917 hasConceptScore W2852420917C33923547 @default.
- W2852420917 hasConceptScore W2852420917C36503486 @default.
- W2852420917 hasConceptScore W2852420917C41008148 @default.
- W2852420917 hasConceptScore W2852420917C41895202 @default.
- W2852420917 hasConceptScore W2852420917C50644808 @default.
- W2852420917 hasConceptScore W2852420917C51632099 @default.
- W2852420917 hasConceptScore W2852420917C61328038 @default.
- W2852420917 hasConceptScore W2852420917C67186912 @default.
- W2852420917 hasConceptScore W2852420917C76155785 @default.
- W2852420917 hasConceptScore W2852420917C77088390 @default.
- W2852420917 hasLocation W28524209171 @default.
- W2852420917 hasOpenAccess W2852420917 @default.
- W2852420917 hasPrimaryLocation W28524209171 @default.
- W2852420917 hasRelatedWork W2852420917 @default.
- W2852420917 hasRelatedWork W2886994463 @default.
- W2852420917 hasRelatedWork W2889705046 @default.
- W2852420917 hasRelatedWork W2949280030 @default.
- W2852420917 hasRelatedWork W2953173049 @default.
- W2852420917 hasRelatedWork W2957568672 @default.
- W2852420917 hasRelatedWork W3099765033 @default.
- W2852420917 hasRelatedWork W3205858688 @default.
- W2852420917 hasRelatedWork W4301607095 @default.
- W2852420917 hasRelatedWork W4312200629 @default.
- W2852420917 isParatext "false" @default.
- W2852420917 isRetracted "false" @default.
- W2852420917 magId "2852420917" @default.
- W2852420917 workType "article" @default.