Matches in SemOpenAlex for { <https://semopenalex.org/work/W2996952407> ?p ?o ?g. }
Showing items 1 to 75 of
75
with 100 items per page.
- W2996952407 endingPage "107175" @default.
- W2996952407 startingPage "107175" @default.
- W2996952407 abstract "Abstract Code-switching (CS) is a multilingual phenomenon where a speaker uses different languages in an utterance or between alternating utterances. Developing large-scale datasets for training code-switching acoustic and language models is challenging and extremely expensive. In this paper, we focus on the acoustic data augmentation for the Mandarin-English CS speech recognition task. Effectiveness of conventional acoustic data augmentation approaches are examined. More importantly, we propose a CS acoustic event detection system based on the deep neural network to extract real code-switching speech segments automatically. Then, the semi-supervised and active learning techniques are investigated to generate transcriptions of these segments. Finally, code-switching speech synthesis system is introduced to further enhance the acoustic modeling. Experimental results on the OC16-CE80 data, a Mandarin-English mixlingual speech corpus, demonstrate the effectiveness of the proposed methods." @default.
- W2996952407 created "2020-01-10" @default.
- W2996952407 creator A5001480103 @default.
- W2996952407 creator A5018064730 @default.
- W2996952407 creator A5039983089 @default.
- W2996952407 creator A5056415893 @default.
- W2996952407 creator A5072176943 @default.
- W2996952407 creator A5075804518 @default.
- W2996952407 date "2020-04-01" @default.
- W2996952407 modified "2023-09-24" @default.
- W2996952407 title "Acoustic data augmentation for Mandarin-English code-switching speech recognition" @default.
- W2996952407 cites W2056200968 @default.
- W2996952407 cites W2742223267 @default.
- W2996952407 cites W2896558859 @default.
- W2996952407 cites W2972417954 @default.
- W2996952407 cites W2972702443 @default.
- W2996952407 cites W2972787773 @default.
- W2996952407 doi "https://doi.org/10.1016/j.apacoust.2019.107175" @default.
- W2996952407 hasPublicationYear "2020" @default.
- W2996952407 type Work @default.
- W2996952407 sameAs 2996952407 @default.
- W2996952407 citedByCount "25" @default.
- W2996952407 countsByYear W29969524072019 @default.
- W2996952407 countsByYear W29969524072020 @default.
- W2996952407 countsByYear W29969524072021 @default.
- W2996952407 countsByYear W29969524072022 @default.
- W2996952407 countsByYear W29969524072023 @default.
- W2996952407 crossrefType "journal-article" @default.
- W2996952407 hasAuthorship W2996952407A5001480103 @default.
- W2996952407 hasAuthorship W2996952407A5018064730 @default.
- W2996952407 hasAuthorship W2996952407A5039983089 @default.
- W2996952407 hasAuthorship W2996952407A5056415893 @default.
- W2996952407 hasAuthorship W2996952407A5072176943 @default.
- W2996952407 hasAuthorship W2996952407A5075804518 @default.
- W2996952407 hasConcept C138885662 @default.
- W2996952407 hasConcept C138954614 @default.
- W2996952407 hasConcept C177264268 @default.
- W2996952407 hasConcept C18552078 @default.
- W2996952407 hasConcept C199360897 @default.
- W2996952407 hasConcept C204321447 @default.
- W2996952407 hasConcept C2776760102 @default.
- W2996952407 hasConcept C28490314 @default.
- W2996952407 hasConcept C41008148 @default.
- W2996952407 hasConcept C41895202 @default.
- W2996952407 hasConceptScore W2996952407C138885662 @default.
- W2996952407 hasConceptScore W2996952407C138954614 @default.
- W2996952407 hasConceptScore W2996952407C177264268 @default.
- W2996952407 hasConceptScore W2996952407C18552078 @default.
- W2996952407 hasConceptScore W2996952407C199360897 @default.
- W2996952407 hasConceptScore W2996952407C204321447 @default.
- W2996952407 hasConceptScore W2996952407C2776760102 @default.
- W2996952407 hasConceptScore W2996952407C28490314 @default.
- W2996952407 hasConceptScore W2996952407C41008148 @default.
- W2996952407 hasConceptScore W2996952407C41895202 @default.
- W2996952407 hasFunder F4320321001 @default.
- W2996952407 hasLocation W29969524071 @default.
- W2996952407 hasOpenAccess W2996952407 @default.
- W2996952407 hasPrimaryLocation W29969524071 @default.
- W2996952407 hasRelatedWork W1517743118 @default.
- W2996952407 hasRelatedWork W1880637544 @default.
- W2996952407 hasRelatedWork W2235320929 @default.
- W2996952407 hasRelatedWork W2347798153 @default.
- W2996952407 hasRelatedWork W2773277385 @default.
- W2996952407 hasRelatedWork W2950896474 @default.
- W2996952407 hasRelatedWork W3143906618 @default.
- W2996952407 hasRelatedWork W3184468331 @default.
- W2996952407 hasRelatedWork W4307308046 @default.
- W2996952407 hasRelatedWork W2277238845 @default.
- W2996952407 hasVolume "161" @default.
- W2996952407 isParatext "false" @default.
- W2996952407 isRetracted "false" @default.
- W2996952407 magId "2996952407" @default.
- W2996952407 workType "article" @default.