Matches in SemOpenAlex for { <https://semopenalex.org/work/W1498717522> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W1498717522 abstract "Deep neural network (DNN) based acoustic modelling has been successfully used for a variety of automatic speech recognition (ASR) tasks, thanks to its ability to learn higher-level information using multiple hidden layers. This paper investigates the recently proposed exemplar-based speech enhancement technique using coupled dictionaries as a pre-processing stage for DNN-based systems. In this setting, the noisy speech is decomposed as a weighted sum of atoms in an input dictionary containing exemplars sampled from a domain of choice, and the resulting weights are applied to a coupled output dictionary containing exemplars sampled in the short-time Fourier transform (STFT) domain to directly obtain the speech and noise estimates for speech enhancement. In this work, settings using input dictionary of exemplars sampled from the STFT, Mel-integrated magnitude STFT and modulation envelope spectra are evaluated. Experiments performed on the AURORA-4 database revealed that these pre-processing stages can improve the performance of the DNN-HMM-based ASR systems with both clean and multi-condition training." @default.
- W1498717522 created "2016-06-24" @default.
- W1498717522 creator A5049691461 @default.
- W1498717522 creator A5061197982 @default.
- W1498717522 creator A5067322015 @default.
- W1498717522 creator A5087514947 @default.
- W1498717522 date "2015-04-01" @default.
- W1498717522 modified "2023-09-27" @default.
- W1498717522 title "Exemplar-based speech enhancement for deep neural network based automatic speech recognition" @default.
- W1498717522 cites W146976060 @default.
- W1498717522 cites W1902027874 @default.
- W1498717522 cites W2016430046 @default.
- W1498717522 cites W2062164080 @default.
- W1498717522 cites W2121973264 @default.
- W1498717522 cites W2129901640 @default.
- W1498717522 cites W2141520175 @default.
- W1498717522 cites W2147768505 @default.
- W1498717522 cites W2160815625 @default.
- W1498717522 cites W2396455701 @default.
- W1498717522 cites W4243044416 @default.
- W1498717522 cites W4255019833 @default.
- W1498717522 cites W44815768 @default.
- W1498717522 doi "https://doi.org/10.1109/icassp.2015.7178819" @default.
- W1498717522 hasPublicationYear "2015" @default.
- W1498717522 type Work @default.
- W1498717522 sameAs 1498717522 @default.
- W1498717522 citedByCount "17" @default.
- W1498717522 countsByYear W14987175222015 @default.
- W1498717522 countsByYear W14987175222016 @default.
- W1498717522 countsByYear W14987175222017 @default.
- W1498717522 countsByYear W14987175222018 @default.
- W1498717522 countsByYear W14987175222019 @default.
- W1498717522 countsByYear W14987175222020 @default.
- W1498717522 countsByYear W14987175222021 @default.
- W1498717522 countsByYear W14987175222022 @default.
- W1498717522 crossrefType "proceedings-article" @default.
- W1498717522 hasAuthorship W1498717522A5049691461 @default.
- W1498717522 hasAuthorship W1498717522A5061197982 @default.
- W1498717522 hasAuthorship W1498717522A5067322015 @default.
- W1498717522 hasAuthorship W1498717522A5087514947 @default.
- W1498717522 hasBestOaLocation W14987175222 @default.
- W1498717522 hasConcept C154945302 @default.
- W1498717522 hasConcept C163294075 @default.
- W1498717522 hasConcept C175202392 @default.
- W1498717522 hasConcept C204201278 @default.
- W1498717522 hasConcept C2776182073 @default.
- W1498717522 hasConcept C28490314 @default.
- W1498717522 hasConcept C2984842247 @default.
- W1498717522 hasConcept C41008148 @default.
- W1498717522 hasConcept C50644808 @default.
- W1498717522 hasConcept C61328038 @default.
- W1498717522 hasConceptScore W1498717522C154945302 @default.
- W1498717522 hasConceptScore W1498717522C163294075 @default.
- W1498717522 hasConceptScore W1498717522C175202392 @default.
- W1498717522 hasConceptScore W1498717522C204201278 @default.
- W1498717522 hasConceptScore W1498717522C2776182073 @default.
- W1498717522 hasConceptScore W1498717522C28490314 @default.
- W1498717522 hasConceptScore W1498717522C2984842247 @default.
- W1498717522 hasConceptScore W1498717522C41008148 @default.
- W1498717522 hasConceptScore W1498717522C50644808 @default.
- W1498717522 hasConceptScore W1498717522C61328038 @default.
- W1498717522 hasLocation W14987175221 @default.
- W1498717522 hasLocation W14987175222 @default.
- W1498717522 hasOpenAccess W1498717522 @default.
- W1498717522 hasPrimaryLocation W14987175221 @default.
- W1498717522 hasRelatedWork W1576113739 @default.
- W1498717522 hasRelatedWork W1679636228 @default.
- W1498717522 hasRelatedWork W2394461504 @default.
- W1498717522 hasRelatedWork W2764005420 @default.
- W1498717522 hasRelatedWork W2988392183 @default.
- W1498717522 hasRelatedWork W3000194274 @default.
- W1498717522 hasRelatedWork W3015358918 @default.
- W1498717522 hasRelatedWork W3135356379 @default.
- W1498717522 hasRelatedWork W3175075966 @default.
- W1498717522 hasRelatedWork W2181728593 @default.
- W1498717522 isParatext "false" @default.
- W1498717522 isRetracted "false" @default.
- W1498717522 magId "1498717522" @default.
- W1498717522 workType "article" @default.