Matches in SemOpenAlex for { <https://semopenalex.org/work/W2783111252> ?p ?o ?g. }
Showing items 1 to 73 of
73
with 100 items per page.
- W2783111252 abstract "Reverberation, which is generally caused by sound reflections from walls, ceilings, and floors, can result in severe performance degradations of acoustic applications. Due to a complicated combination of attenuation and time-delay effects, the reverberation property is difficult to characterize, and it remains a challenging task to effectively retrieve the anechoic speech signals from reverberation ones. In the present study, we proposed a novel integrated deep and ensemble learning (IDEL) algorithm for speech dereverberation. The IDEL algorithm consists of offline and online phases. In the offline phase, we train multiple dereverberation models, each aiming to precisely dereverb speech signals in a particular acoustic environment; then a unified fusion function is estimated that aims to integrate the information of multiple dereverberation models. In the online phase, an input utterance is first processed by each of the dereverberation models. The outputs of all models are integrated accordingly to generate the final anechoic signal. We evaluated IDEL on designed acoustic environments, including both matched and mismatched conditions of the training and testing data. Experimental results confirm that the proposed IDEL algorithm outperforms single deep-neural-network-based dereverberation model with the same model architecture and training data." @default.
- W2783111252 created "2018-01-26" @default.
- W2783111252 creator A5009305504 @default.
- W2783111252 creator A5034792613 @default.
- W2783111252 creator A5044008055 @default.
- W2783111252 creator A5054709496 @default.
- W2783111252 creator A5067950969 @default.
- W2783111252 creator A5073046122 @default.
- W2783111252 date "2018-01-12" @default.
- W2783111252 modified "2023-09-22" @default.
- W2783111252 title "Speech Dereverberation Based on Integrated Deep and Ensemble Learning." @default.
- W2783111252 hasPublicationYear "2018" @default.
- W2783111252 type Work @default.
- W2783111252 sameAs 2783111252 @default.
- W2783111252 citedByCount "0" @default.
- W2783111252 crossrefType "posted-content" @default.
- W2783111252 hasAuthorship W2783111252A5009305504 @default.
- W2783111252 hasAuthorship W2783111252A5034792613 @default.
- W2783111252 hasAuthorship W2783111252A5044008055 @default.
- W2783111252 hasAuthorship W2783111252A5054709496 @default.
- W2783111252 hasAuthorship W2783111252A5067950969 @default.
- W2783111252 hasAuthorship W2783111252A5073046122 @default.
- W2783111252 hasConcept C108583219 @default.
- W2783111252 hasConcept C121332964 @default.
- W2783111252 hasConcept C149712133 @default.
- W2783111252 hasConcept C154945302 @default.
- W2783111252 hasConcept C199360897 @default.
- W2783111252 hasConcept C24890656 @default.
- W2783111252 hasConcept C2775852435 @default.
- W2783111252 hasConcept C2779843651 @default.
- W2783111252 hasConcept C28490314 @default.
- W2783111252 hasConcept C41008148 @default.
- W2783111252 hasConcept C76155785 @default.
- W2783111252 hasConcept C95851461 @default.
- W2783111252 hasConceptScore W2783111252C108583219 @default.
- W2783111252 hasConceptScore W2783111252C121332964 @default.
- W2783111252 hasConceptScore W2783111252C149712133 @default.
- W2783111252 hasConceptScore W2783111252C154945302 @default.
- W2783111252 hasConceptScore W2783111252C199360897 @default.
- W2783111252 hasConceptScore W2783111252C24890656 @default.
- W2783111252 hasConceptScore W2783111252C2775852435 @default.
- W2783111252 hasConceptScore W2783111252C2779843651 @default.
- W2783111252 hasConceptScore W2783111252C28490314 @default.
- W2783111252 hasConceptScore W2783111252C41008148 @default.
- W2783111252 hasConceptScore W2783111252C76155785 @default.
- W2783111252 hasConceptScore W2783111252C95851461 @default.
- W2783111252 hasLocation W27831112521 @default.
- W2783111252 hasOpenAccess W2783111252 @default.
- W2783111252 hasPrimaryLocation W27831112521 @default.
- W2783111252 hasRelatedWork W120286663 @default.
- W2783111252 hasRelatedWork W16490680 @default.
- W2783111252 hasRelatedWork W1919103499 @default.
- W2783111252 hasRelatedWork W2017519504 @default.
- W2783111252 hasRelatedWork W2062355771 @default.
- W2783111252 hasRelatedWork W2125539885 @default.
- W2783111252 hasRelatedWork W2141418660 @default.
- W2783111252 hasRelatedWork W2276077954 @default.
- W2783111252 hasRelatedWork W2474646974 @default.
- W2783111252 hasRelatedWork W2736172179 @default.
- W2783111252 hasRelatedWork W2766439643 @default.
- W2783111252 hasRelatedWork W2772504888 @default.
- W2783111252 hasRelatedWork W2793675140 @default.
- W2783111252 hasRelatedWork W3015679215 @default.
- W2783111252 hasRelatedWork W3026111682 @default.
- W2783111252 hasRelatedWork W3137952414 @default.
- W2783111252 hasRelatedWork W3153879011 @default.
- W2783111252 hasRelatedWork W3197704003 @default.
- W2783111252 hasRelatedWork W2201738735 @default.
- W2783111252 hasRelatedWork W2589165278 @default.
- W2783111252 isParatext "false" @default.
- W2783111252 isRetracted "false" @default.
- W2783111252 magId "2783111252" @default.
- W2783111252 workType "article" @default.