Matches in SemOpenAlex for { <https://semopenalex.org/work/W2397940721> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W2397940721 abstract "The language identification (LID) task in the Robust Automatic Transcription of Speech (RATS) program is challenging due to the noisy nature of the audio data collected over highly degraded radio communication channels as well as the use of short duration speech segments for testing. In this paper, we report the recent advances made in the RATS LID task by using bottleneck features from a convolutional neural network (CNN). The CNN, which is trained with labelled data from one of target languages, generates bottleneck features which are used in a Gaussian mixture model (GMM)-ivector LID system. The CNN bottleneck features provide substantial complimentary information to the conventional acoustic features even on languages not seen in its training. Using these bottleneck features in conjunction with acoustic features, we obtain significant improvements (average relative improvements of 25% in terms of equal error rate (EER) compared to the corresponding acoustic system) for the LID task. Furthermore, these improvements are consistent for various choices of acoustic features as well as speech segment durations." @default.
- W2397940721 created "2016-06-24" @default.
- W2397940721 creator A5002536077 @default.
- W2397940721 creator A5010028928 @default.
- W2397940721 creator A5016030542 @default.
- W2397940721 creator A5038419298 @default.
- W2397940721 creator A5056869363 @default.
- W2397940721 creator A5089387678 @default.
- W2397940721 date "2014-09-14" @default.
- W2397940721 modified "2023-09-26" @default.
- W2397940721 title "Robust language identification using convolutional neural network features" @default.
- W2397940721 cites W2009150118 @default.
- W2397940721 cites W2088137865 @default.
- W2397940721 cites W2112796928 @default.
- W2397940721 cites W2113932204 @default.
- W2397940721 cites W2114719288 @default.
- W2397940721 cites W2142730757 @default.
- W2397940721 cites W2148154194 @default.
- W2397940721 cites W2155273149 @default.
- W2397940721 cites W2172287020 @default.
- W2397940721 cites W2274548782 @default.
- W2397940721 cites W2293851464 @default.
- W2397940721 cites W2398527292 @default.
- W2397940721 cites W2399270979 @default.
- W2397940721 cites W2405787239 @default.
- W2397940721 cites W2408021097 @default.
- W2397940721 cites W2887979278 @default.
- W2397940721 cites W41021157 @default.
- W2397940721 doi "https://doi.org/10.21437/interspeech.2014-419" @default.
- W2397940721 hasPublicationYear "2014" @default.
- W2397940721 type Work @default.
- W2397940721 sameAs 2397940721 @default.
- W2397940721 citedByCount "27" @default.
- W2397940721 countsByYear W23979407212015 @default.
- W2397940721 countsByYear W23979407212016 @default.
- W2397940721 countsByYear W23979407212017 @default.
- W2397940721 countsByYear W23979407212018 @default.
- W2397940721 countsByYear W23979407212019 @default.
- W2397940721 countsByYear W23979407212020 @default.
- W2397940721 countsByYear W23979407212021 @default.
- W2397940721 countsByYear W23979407212022 @default.
- W2397940721 countsByYear W23979407212023 @default.
- W2397940721 crossrefType "proceedings-article" @default.
- W2397940721 hasAuthorship W2397940721A5002536077 @default.
- W2397940721 hasAuthorship W2397940721A5010028928 @default.
- W2397940721 hasAuthorship W2397940721A5016030542 @default.
- W2397940721 hasAuthorship W2397940721A5038419298 @default.
- W2397940721 hasAuthorship W2397940721A5056869363 @default.
- W2397940721 hasAuthorship W2397940721A5089387678 @default.
- W2397940721 hasConcept C116834253 @default.
- W2397940721 hasConcept C129792486 @default.
- W2397940721 hasConcept C154945302 @default.
- W2397940721 hasConcept C195324797 @default.
- W2397940721 hasConcept C204321447 @default.
- W2397940721 hasConcept C41008148 @default.
- W2397940721 hasConcept C59822182 @default.
- W2397940721 hasConcept C81363708 @default.
- W2397940721 hasConcept C86803240 @default.
- W2397940721 hasConceptScore W2397940721C116834253 @default.
- W2397940721 hasConceptScore W2397940721C129792486 @default.
- W2397940721 hasConceptScore W2397940721C154945302 @default.
- W2397940721 hasConceptScore W2397940721C195324797 @default.
- W2397940721 hasConceptScore W2397940721C204321447 @default.
- W2397940721 hasConceptScore W2397940721C41008148 @default.
- W2397940721 hasConceptScore W2397940721C59822182 @default.
- W2397940721 hasConceptScore W2397940721C81363708 @default.
- W2397940721 hasConceptScore W2397940721C86803240 @default.
- W2397940721 hasLocation W23979407211 @default.
- W2397940721 hasOpenAccess W2397940721 @default.
- W2397940721 hasPrimaryLocation W23979407211 @default.
- W2397940721 hasRelatedWork W2735477435 @default.
- W2397940721 hasRelatedWork W2748454020 @default.
- W2397940721 hasRelatedWork W2805908200 @default.
- W2397940721 hasRelatedWork W2807436399 @default.
- W2397940721 hasRelatedWork W3001728219 @default.
- W2397940721 hasRelatedWork W3016958897 @default.
- W2397940721 hasRelatedWork W3045739591 @default.
- W2397940721 hasRelatedWork W3181746755 @default.
- W2397940721 hasRelatedWork W4283379348 @default.
- W2397940721 hasRelatedWork W4312417841 @default.
- W2397940721 isParatext "false" @default.
- W2397940721 isRetracted "false" @default.
- W2397940721 magId "2397940721" @default.
- W2397940721 workType "article" @default.