Matches in SemOpenAlex for { <https://semopenalex.org/work/W3200575128> ?p ?o ?g. }
Showing items 1 to 95 of
95
with 100 items per page.
- W3200575128 abstract "In this work, we propose a novel approach for visual voice activity detection (VAD), which is an important component of audio-visual tasks such as speech enhancement. We focus on optimizing the visual component and propose a two-stream approach based on optical flow and RGB data. Both streams are analyzed by long short-term memory (LSTM) modules to extract dynamic features. We show that this setup clearly improves the one without optical flow. Additionally, we show that focusing on the lower face area is superior to processing the whole face, or only the mouth region as usually done. This aspect involves practical advantages, since it facilitates data labeling. Our approach especially improves the true negative rate, which means we detect frames without speech more reliably—we see the silence." @default.
- W3200575128 created "2021-09-27" @default.
- W3200575128 creator A5023952427 @default.
- W3200575128 creator A5038082633 @default.
- W3200575128 creator A5064239504 @default.
- W3200575128 creator A5087022569 @default.
- W3200575128 date "2021-01-01" @default.
- W3200575128 modified "2023-09-26" @default.
- W3200575128 title "See the Silence: Improving Visual-Only Voice Activity Detection by Optical Flow and RGB Fusion" @default.
- W3200575128 cites W1583001605 @default.
- W3200575128 cites W1755205674 @default.
- W3200575128 cites W1973067693 @default.
- W3200575128 cites W1985242443 @default.
- W3200575128 cites W2015241216 @default.
- W3200575128 cites W2029199293 @default.
- W3200575128 cites W2098923380 @default.
- W3200575128 cites W2118354544 @default.
- W3200575128 cites W2129120544 @default.
- W3200575128 cites W2150125142 @default.
- W3200575128 cites W2171330332 @default.
- W3200575128 cites W2330149154 @default.
- W3200575128 cites W2405180117 @default.
- W3200575128 cites W2512215050 @default.
- W3200575128 cites W2517379296 @default.
- W3200575128 cites W2559837139 @default.
- W3200575128 cites W2735559731 @default.
- W3200575128 cites W2917987043 @default.
- W3200575128 cites W2963066927 @default.
- W3200575128 cites W2970250044 @default.
- W3200575128 cites W3040865677 @default.
- W3200575128 cites W3119269912 @default.
- W3200575128 cites W4245919820 @default.
- W3200575128 doi "https://doi.org/10.1007/978-3-030-87156-7_4" @default.
- W3200575128 hasPublicationYear "2021" @default.
- W3200575128 type Work @default.
- W3200575128 sameAs 3200575128 @default.
- W3200575128 citedByCount "0" @default.
- W3200575128 crossrefType "book-chapter" @default.
- W3200575128 hasAuthorship W3200575128A5023952427 @default.
- W3200575128 hasAuthorship W3200575128A5038082633 @default.
- W3200575128 hasAuthorship W3200575128A5064239504 @default.
- W3200575128 hasAuthorship W3200575128A5087022569 @default.
- W3200575128 hasConcept C107038049 @default.
- W3200575128 hasConcept C115961682 @default.
- W3200575128 hasConcept C120665830 @default.
- W3200575128 hasConcept C121332964 @default.
- W3200575128 hasConcept C138885662 @default.
- W3200575128 hasConcept C144024400 @default.
- W3200575128 hasConcept C154945302 @default.
- W3200575128 hasConcept C155542232 @default.
- W3200575128 hasConcept C168167062 @default.
- W3200575128 hasConcept C192209626 @default.
- W3200575128 hasConcept C2779304628 @default.
- W3200575128 hasConcept C2781115785 @default.
- W3200575128 hasConcept C28490314 @default.
- W3200575128 hasConcept C31972630 @default.
- W3200575128 hasConcept C36289849 @default.
- W3200575128 hasConcept C41008148 @default.
- W3200575128 hasConcept C82990744 @default.
- W3200575128 hasConcept C97355855 @default.
- W3200575128 hasConceptScore W3200575128C107038049 @default.
- W3200575128 hasConceptScore W3200575128C115961682 @default.
- W3200575128 hasConceptScore W3200575128C120665830 @default.
- W3200575128 hasConceptScore W3200575128C121332964 @default.
- W3200575128 hasConceptScore W3200575128C138885662 @default.
- W3200575128 hasConceptScore W3200575128C144024400 @default.
- W3200575128 hasConceptScore W3200575128C154945302 @default.
- W3200575128 hasConceptScore W3200575128C155542232 @default.
- W3200575128 hasConceptScore W3200575128C168167062 @default.
- W3200575128 hasConceptScore W3200575128C192209626 @default.
- W3200575128 hasConceptScore W3200575128C2779304628 @default.
- W3200575128 hasConceptScore W3200575128C2781115785 @default.
- W3200575128 hasConceptScore W3200575128C28490314 @default.
- W3200575128 hasConceptScore W3200575128C31972630 @default.
- W3200575128 hasConceptScore W3200575128C36289849 @default.
- W3200575128 hasConceptScore W3200575128C41008148 @default.
- W3200575128 hasConceptScore W3200575128C82990744 @default.
- W3200575128 hasConceptScore W3200575128C97355855 @default.
- W3200575128 hasLocation W32005751281 @default.
- W3200575128 hasOpenAccess W3200575128 @default.
- W3200575128 hasPrimaryLocation W32005751281 @default.
- W3200575128 hasRelatedWork W11527430 @default.
- W3200575128 hasRelatedWork W13187899 @default.
- W3200575128 hasRelatedWork W13423774 @default.
- W3200575128 hasRelatedWork W1889328 @default.
- W3200575128 hasRelatedWork W2583009 @default.
- W3200575128 hasRelatedWork W4997609 @default.
- W3200575128 hasRelatedWork W6614869 @default.
- W3200575128 hasRelatedWork W8340350 @default.
- W3200575128 hasRelatedWork W12749109 @default.
- W3200575128 hasRelatedWork W630671 @default.
- W3200575128 isParatext "false" @default.
- W3200575128 isRetracted "false" @default.
- W3200575128 magId "3200575128" @default.
- W3200575128 workType "book-chapter" @default.