Matches in SemOpenAlex for { <https://semopenalex.org/work/W2886232760> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W2886232760 abstract "Human auditory cortex excels at selectively suppressing background noise to focus on a target speaker. The process of selective attention in the brain is known to contextually exploit the available audio and visual cues to better focus on target speaker while filtering out other noises. In this study, we propose a novel deep neural network (DNN) based audiovisual (AV) mask estimation model. The proposed AV mask estimation model contextually integrates the temporal dynamics of both audio and noise-immune visual features for improved mask estimation and speech separation. For optimal AV features extraction and ideal binary mask (IBM) estimation, a hybrid DNN architecture is exploited to leverages the complementary strengths of a stacked long short term memory (LSTM) and convolution LSTM network. The comparative simulation results in terms of speech quality and intelligibility demonstrate significant performance improvement of our proposed AV mask estimation model as compared to audio-only and visual-only mask estimation approaches for both speaker dependent and independent scenarios." @default.
- W2886232760 created "2018-08-22" @default.
- W2886232760 creator A5013266148 @default.
- W2886232760 creator A5062211930 @default.
- W2886232760 creator A5068981769 @default.
- W2886232760 creator A5074458312 @default.
- W2886232760 creator A5082626629 @default.
- W2886232760 date "2018-09-02" @default.
- W2886232760 modified "2023-10-02" @default.
- W2886232760 title "DNN Driven Speaker Independent Audio-Visual Mask Estimation for Speech Separation" @default.
- W2886232760 cites W2003203076 @default.
- W2886232760 cites W2012910847 @default.
- W2886232760 cites W2015143272 @default.
- W2886232760 cites W2018651852 @default.
- W2886232760 cites W2027701650 @default.
- W2886232760 cites W2035576074 @default.
- W2886232760 cites W2043216213 @default.
- W2886232760 cites W2141411743 @default.
- W2886232760 cites W2164598857 @default.
- W2886232760 cites W2398042854 @default.
- W2886232760 cites W2678916739 @default.
- W2886232760 cites W2746601360 @default.
- W2886232760 cites W2787592166 @default.
- W2886232760 cites W2964121744 @default.
- W2886232760 doi "https://doi.org/10.21437/interspeech.2018-2516" @default.
- W2886232760 hasPublicationYear "2018" @default.
- W2886232760 type Work @default.
- W2886232760 sameAs 2886232760 @default.
- W2886232760 citedByCount "29" @default.
- W2886232760 countsByYear W28862327602018 @default.
- W2886232760 countsByYear W28862327602019 @default.
- W2886232760 countsByYear W28862327602020 @default.
- W2886232760 countsByYear W28862327602021 @default.
- W2886232760 countsByYear W28862327602022 @default.
- W2886232760 countsByYear W28862327602023 @default.
- W2886232760 crossrefType "proceedings-article" @default.
- W2886232760 hasAuthorship W2886232760A5013266148 @default.
- W2886232760 hasAuthorship W2886232760A5062211930 @default.
- W2886232760 hasAuthorship W2886232760A5068981769 @default.
- W2886232760 hasAuthorship W2886232760A5074458312 @default.
- W2886232760 hasAuthorship W2886232760A5082626629 @default.
- W2886232760 hasBestOaLocation W28862327602 @default.
- W2886232760 hasConcept C111472728 @default.
- W2886232760 hasConcept C115961682 @default.
- W2886232760 hasConcept C120665830 @default.
- W2886232760 hasConcept C121332964 @default.
- W2886232760 hasConcept C138885662 @default.
- W2886232760 hasConcept C153180895 @default.
- W2886232760 hasConcept C154945302 @default.
- W2886232760 hasConcept C192209626 @default.
- W2886232760 hasConcept C28490314 @default.
- W2886232760 hasConcept C41008148 @default.
- W2886232760 hasConcept C50644808 @default.
- W2886232760 hasConcept C60048801 @default.
- W2886232760 hasConcept C99498987 @default.
- W2886232760 hasConceptScore W2886232760C111472728 @default.
- W2886232760 hasConceptScore W2886232760C115961682 @default.
- W2886232760 hasConceptScore W2886232760C120665830 @default.
- W2886232760 hasConceptScore W2886232760C121332964 @default.
- W2886232760 hasConceptScore W2886232760C138885662 @default.
- W2886232760 hasConceptScore W2886232760C153180895 @default.
- W2886232760 hasConceptScore W2886232760C154945302 @default.
- W2886232760 hasConceptScore W2886232760C192209626 @default.
- W2886232760 hasConceptScore W2886232760C28490314 @default.
- W2886232760 hasConceptScore W2886232760C41008148 @default.
- W2886232760 hasConceptScore W2886232760C50644808 @default.
- W2886232760 hasConceptScore W2886232760C60048801 @default.
- W2886232760 hasConceptScore W2886232760C99498987 @default.
- W2886232760 hasLocation W28862327601 @default.
- W2886232760 hasLocation W28862327602 @default.
- W2886232760 hasLocation W28862327603 @default.
- W2886232760 hasLocation W28862327604 @default.
- W2886232760 hasLocation W28862327605 @default.
- W2886232760 hasLocation W28862327606 @default.
- W2886232760 hasLocation W28862327607 @default.
- W2886232760 hasLocation W28862327608 @default.
- W2886232760 hasOpenAccess W2886232760 @default.
- W2886232760 hasPrimaryLocation W28862327601 @default.
- W2886232760 hasRelatedWork W2015192756 @default.
- W2886232760 hasRelatedWork W2033914206 @default.
- W2886232760 hasRelatedWork W2042327336 @default.
- W2886232760 hasRelatedWork W2046077695 @default.
- W2886232760 hasRelatedWork W2127461790 @default.
- W2886232760 hasRelatedWork W2146076056 @default.
- W2886232760 hasRelatedWork W2163831990 @default.
- W2886232760 hasRelatedWork W2378160586 @default.
- W2886232760 hasRelatedWork W2386387936 @default.
- W2886232760 hasRelatedWork W3003836766 @default.
- W2886232760 isParatext "false" @default.
- W2886232760 isRetracted "false" @default.
- W2886232760 magId "2886232760" @default.
- W2886232760 workType "article" @default.