Matches in SemOpenAlex for { <https://semopenalex.org/work/W3201659743> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3201659743 endingPage "404" @default.
- W3201659743 startingPage "394" @default.
- W3201659743 abstract "In this paper, we explore the benefits of incorporating context into a Recurrent Neural Network (RNN-T) based Automatic Speech Recognition (ASR) model to improve the speech recognition for virtual assistants. Specifically, we use meta information extracted from the time at which the utterance is spoken and the approximate location information to make ASR context aware. We show that these contextual information, when used individually, improves overall performance by as much as 3.48% relative to the baseline and when the contexts are combined, the model learns complementary features and the recognition improves by 4.62%. On specific domains, these contextual signals show improvements as high as 11.5%, without any significant degradation on others. We ran experiments with models trained on data of sizes 30K hours and 10K hours. We show that the scale of improvement with the 10K hours dataset is much higher than the one obtained with 30K hours dataset. Our results indicate that with limited data to train the ASR model, contextual signals can improve the performance significantly." @default.
- W3201659743 created "2021-10-11" @default.
- W3201659743 creator A5032932928 @default.
- W3201659743 creator A5059221392 @default.
- W3201659743 creator A5067669848 @default.
- W3201659743 creator A5078650374 @default.
- W3201659743 date "2021-01-01" @default.
- W3201659743 modified "2023-09-24" @default.
- W3201659743 title "Improving RNN-T ASR Performance with Date-Time and Location Awareness" @default.
- W3201659743 cites W1999965501 @default.
- W3201659743 cites W2127141656 @default.
- W3201659743 cites W2327501763 @default.
- W3201659743 cites W2586813637 @default.
- W3201659743 cites W2799119017 @default.
- W3201659743 cites W2890410208 @default.
- W3201659743 cites W2936774411 @default.
- W3201659743 cites W2963626743 @default.
- W3201659743 cites W2964045208 @default.
- W3201659743 cites W3015760975 @default.
- W3201659743 cites W4249179470 @default.
- W3201659743 doi "https://doi.org/10.1007/978-3-030-83527-9_33" @default.
- W3201659743 hasPublicationYear "2021" @default.
- W3201659743 type Work @default.
- W3201659743 sameAs 3201659743 @default.
- W3201659743 citedByCount "1" @default.
- W3201659743 countsByYear W32016597432023 @default.
- W3201659743 crossrefType "book-chapter" @default.
- W3201659743 hasAuthorship W3201659743A5032932928 @default.
- W3201659743 hasAuthorship W3201659743A5059221392 @default.
- W3201659743 hasAuthorship W3201659743A5067669848 @default.
- W3201659743 hasAuthorship W3201659743A5078650374 @default.
- W3201659743 hasBestOaLocation W32016597432 @default.
- W3201659743 hasConcept C111368507 @default.
- W3201659743 hasConcept C119857082 @default.
- W3201659743 hasConcept C12725497 @default.
- W3201659743 hasConcept C127313418 @default.
- W3201659743 hasConcept C137293760 @default.
- W3201659743 hasConcept C147168706 @default.
- W3201659743 hasConcept C151730666 @default.
- W3201659743 hasConcept C154945302 @default.
- W3201659743 hasConcept C2775852435 @default.
- W3201659743 hasConcept C2779343474 @default.
- W3201659743 hasConcept C2781238097 @default.
- W3201659743 hasConcept C28490314 @default.
- W3201659743 hasConcept C41008148 @default.
- W3201659743 hasConcept C50644808 @default.
- W3201659743 hasConcept C71611378 @default.
- W3201659743 hasConcept C86803240 @default.
- W3201659743 hasConceptScore W3201659743C111368507 @default.
- W3201659743 hasConceptScore W3201659743C119857082 @default.
- W3201659743 hasConceptScore W3201659743C12725497 @default.
- W3201659743 hasConceptScore W3201659743C127313418 @default.
- W3201659743 hasConceptScore W3201659743C137293760 @default.
- W3201659743 hasConceptScore W3201659743C147168706 @default.
- W3201659743 hasConceptScore W3201659743C151730666 @default.
- W3201659743 hasConceptScore W3201659743C154945302 @default.
- W3201659743 hasConceptScore W3201659743C2775852435 @default.
- W3201659743 hasConceptScore W3201659743C2779343474 @default.
- W3201659743 hasConceptScore W3201659743C2781238097 @default.
- W3201659743 hasConceptScore W3201659743C28490314 @default.
- W3201659743 hasConceptScore W3201659743C41008148 @default.
- W3201659743 hasConceptScore W3201659743C50644808 @default.
- W3201659743 hasConceptScore W3201659743C71611378 @default.
- W3201659743 hasConceptScore W3201659743C86803240 @default.
- W3201659743 hasLocation W32016597431 @default.
- W3201659743 hasLocation W32016597432 @default.
- W3201659743 hasOpenAccess W3201659743 @default.
- W3201659743 hasPrimaryLocation W32016597431 @default.
- W3201659743 hasRelatedWork W1499864241 @default.
- W3201659743 hasRelatedWork W2046811668 @default.
- W3201659743 hasRelatedWork W2080458333 @default.
- W3201659743 hasRelatedWork W2147212219 @default.
- W3201659743 hasRelatedWork W2782005958 @default.
- W3201659743 hasRelatedWork W2896411932 @default.
- W3201659743 hasRelatedWork W2963414781 @default.
- W3201659743 hasRelatedWork W3151526698 @default.
- W3201659743 hasRelatedWork W3166193157 @default.
- W3201659743 hasRelatedWork W4287121028 @default.
- W3201659743 isParatext "false" @default.
- W3201659743 isRetracted "false" @default.
- W3201659743 magId "3201659743" @default.
- W3201659743 workType "book-chapter" @default.