Matches in SemOpenAlex for { <https://semopenalex.org/work/W4224917961> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4224917961 abstract "End-to-end (E2E) Automatic Speech Recognition (ASR) systems are widely applied in various devices and communication domains. However, state-of-the-art ASR systems are known to underperform when there is a mismatch in the training and test domains. As a result, acoustic models deployed in production are often adapted to the target domain to improve accuracy. This paper proposes a method to perform unsupervised model adaptation for E2E ASR using first-pass transcriptions of adaptation data produced by the baseline ASR model itself. The paper proposes two transcription confidence measures that can be used to select an optimal in-domain adaptation set. Experiments were performed using the Quartznet ASR architecture on the HarperValleyBank corpus. Results show that the unsupervised adaptation technique with the confidence measure based data selection results in a 8% absolute reduction in word error rate on the HarperValleyBank test set. The proposed method can be applied to any E2E ASR system and is suitable for model adaptation on call center audio with little to no manual transcription." @default.
- W4224917961 created "2022-04-28" @default.
- W4224917961 creator A5004762529 @default.
- W4224917961 creator A5010032071 @default.
- W4224917961 creator A5055256533 @default.
- W4224917961 creator A5067587104 @default.
- W4224917961 date "2022-05-23" @default.
- W4224917961 modified "2023-09-27" @default.
- W4224917961 title "Unsupervised Model Adaptation for End-to-End ASR" @default.
- W4224917961 cites W1795658042 @default.
- W4224917961 cites W1989549063 @default.
- W4224917961 cites W2010362084 @default.
- W4224917961 cites W2079623482 @default.
- W4224917961 cites W2094147890 @default.
- W4224917961 cites W2155648385 @default.
- W4224917961 cites W2743818757 @default.
- W4224917961 cites W2791636785 @default.
- W4224917961 cites W2802270051 @default.
- W4224917961 cites W2889374926 @default.
- W4224917961 cites W2891816510 @default.
- W4224917961 cites W2891980359 @default.
- W4224917961 cites W2939216642 @default.
- W4224917961 cites W3015537910 @default.
- W4224917961 cites W3094721881 @default.
- W4224917961 cites W3095315336 @default.
- W4224917961 cites W3161324588 @default.
- W4224917961 doi "https://doi.org/10.1109/icassp43922.2022.9746188" @default.
- W4224917961 hasPublicationYear "2022" @default.
- W4224917961 type Work @default.
- W4224917961 citedByCount "1" @default.
- W4224917961 countsByYear W42249179612023 @default.
- W4224917961 crossrefType "proceedings-article" @default.
- W4224917961 hasAuthorship W4224917961A5004762529 @default.
- W4224917961 hasAuthorship W4224917961A5010032071 @default.
- W4224917961 hasAuthorship W4224917961A5055256533 @default.
- W4224917961 hasAuthorship W4224917961A5067587104 @default.
- W4224917961 hasConcept C120665830 @default.
- W4224917961 hasConcept C121332964 @default.
- W4224917961 hasConcept C138885662 @default.
- W4224917961 hasConcept C139807058 @default.
- W4224917961 hasConcept C154945302 @default.
- W4224917961 hasConcept C155635449 @default.
- W4224917961 hasConcept C169903167 @default.
- W4224917961 hasConcept C177264268 @default.
- W4224917961 hasConcept C179926584 @default.
- W4224917961 hasConcept C199360897 @default.
- W4224917961 hasConcept C2776434776 @default.
- W4224917961 hasConcept C28490314 @default.
- W4224917961 hasConcept C40969351 @default.
- W4224917961 hasConcept C41008148 @default.
- W4224917961 hasConcept C41895202 @default.
- W4224917961 hasConcept C61328038 @default.
- W4224917961 hasConcept C74296488 @default.
- W4224917961 hasConcept C81917197 @default.
- W4224917961 hasConcept C90805587 @default.
- W4224917961 hasConcept C95623464 @default.
- W4224917961 hasConceptScore W4224917961C120665830 @default.
- W4224917961 hasConceptScore W4224917961C121332964 @default.
- W4224917961 hasConceptScore W4224917961C138885662 @default.
- W4224917961 hasConceptScore W4224917961C139807058 @default.
- W4224917961 hasConceptScore W4224917961C154945302 @default.
- W4224917961 hasConceptScore W4224917961C155635449 @default.
- W4224917961 hasConceptScore W4224917961C169903167 @default.
- W4224917961 hasConceptScore W4224917961C177264268 @default.
- W4224917961 hasConceptScore W4224917961C179926584 @default.
- W4224917961 hasConceptScore W4224917961C199360897 @default.
- W4224917961 hasConceptScore W4224917961C2776434776 @default.
- W4224917961 hasConceptScore W4224917961C28490314 @default.
- W4224917961 hasConceptScore W4224917961C40969351 @default.
- W4224917961 hasConceptScore W4224917961C41008148 @default.
- W4224917961 hasConceptScore W4224917961C41895202 @default.
- W4224917961 hasConceptScore W4224917961C61328038 @default.
- W4224917961 hasConceptScore W4224917961C74296488 @default.
- W4224917961 hasConceptScore W4224917961C81917197 @default.
- W4224917961 hasConceptScore W4224917961C90805587 @default.
- W4224917961 hasConceptScore W4224917961C95623464 @default.
- W4224917961 hasLocation W42249179611 @default.
- W4224917961 hasOpenAccess W4224917961 @default.
- W4224917961 hasPrimaryLocation W42249179611 @default.
- W4224917961 hasRelatedWork W1878900550 @default.
- W4224917961 hasRelatedWork W2008308193 @default.
- W4224917961 hasRelatedWork W2017555767 @default.
- W4224917961 hasRelatedWork W2165136106 @default.
- W4224917961 hasRelatedWork W2520160253 @default.
- W4224917961 hasRelatedWork W3151744761 @default.
- W4224917961 hasRelatedWork W3162105464 @default.
- W4224917961 hasRelatedWork W4224917961 @default.
- W4224917961 hasRelatedWork W4310609044 @default.
- W4224917961 hasRelatedWork W4319779560 @default.
- W4224917961 isParatext "false" @default.
- W4224917961 isRetracted "false" @default.
- W4224917961 workType "article" @default.