Matches in SemOpenAlex for { <https://semopenalex.org/work/W2240641835> ?p ?o ?g. }
- W2240641835 endingPage "256" @default.
- W2240641835 startingPage "252" @default.
- W2240641835 abstract "Voice Activity Detection (VAD) refers to the problem of distinguishing speech segments from background noise. Numerous approaches have been proposed for this purpose. Some are based on features derived from the power spectral density, others exploit the periodicity of the signal. The goal of this paper is to investigate the joint use of source and filter-based features. Interestingly, a mutual information-based assessment shows superior discrimination power for the source-related features, especially the proposed ones. The features are further the input of an artificial neural network-based classifier trained on a multi-condition database. Two strategies are proposed to merge source and filter information: feature and decision fusion. Our experiments indicate an absolute reduction of 3% of the equal error rate when using decision fusion. The final proposed system is compared to four state-of-the-art methods on 150 minutes of data recorded in real environments. Thanks to the robustness of its source-related features, its multi-condition training and its efficient information fusion, the proposed system yields over the best state-of-the-art VAD a substantial increase of accuracy across all conditions (24% absolute on average)." @default.
- W2240641835 created "2016-06-24" @default.
- W2240641835 creator A5007918498 @default.
- W2240641835 creator A5027907338 @default.
- W2240641835 creator A5029023520 @default.
- W2240641835 creator A5035745788 @default.
- W2240641835 date "2016-02-01" @default.
- W2240641835 modified "2023-10-10" @default.
- W2240641835 title "Voice Activity Detection: Merging Source and Filter-based Information" @default.
- W2240641835 cites W1965559434 @default.
- W2240641835 cites W1975748432 @default.
- W2240641835 cites W1981341575 @default.
- W2240641835 cites W1999319498 @default.
- W2240641835 cites W1999454387 @default.
- W2240641835 cites W2023582935 @default.
- W2240641835 cites W2023684629 @default.
- W2240641835 cites W2029147192 @default.
- W2240641835 cites W2052043304 @default.
- W2240641835 cites W2052384514 @default.
- W2240641835 cites W2073693905 @default.
- W2240641835 cites W2090861223 @default.
- W2240641835 cites W2095176743 @default.
- W2240641835 cites W2098265087 @default.
- W2240641835 cites W2099076569 @default.
- W2240641835 cites W2115717467 @default.
- W2240641835 cites W2117468249 @default.
- W2240641835 cites W2126693545 @default.
- W2240641835 cites W2129120544 @default.
- W2240641835 cites W2130814876 @default.
- W2240641835 cites W2132214951 @default.
- W2240641835 cites W2142170306 @default.
- W2240641835 cites W2149053750 @default.
- W2240641835 cites W2154278880 @default.
- W2240641835 cites W2156038773 @default.
- W2240641835 cites W2156798212 @default.
- W2240641835 cites W2158275940 @default.
- W2240641835 cites W2158353947 @default.
- W2240641835 cites W2165034386 @default.
- W2240641835 cites W2170644918 @default.
- W2240641835 cites W2397375888 @default.
- W2240641835 cites W2402212287 @default.
- W2240641835 cites W2403186097 @default.
- W2240641835 cites W304112886 @default.
- W2240641835 cites W36345725 @default.
- W2240641835 cites W4237171445 @default.
- W2240641835 cites W86289693 @default.
- W2240641835 doi "https://doi.org/10.1109/lsp.2015.2495219" @default.
- W2240641835 hasPublicationYear "2016" @default.
- W2240641835 type Work @default.
- W2240641835 sameAs 2240641835 @default.
- W2240641835 citedByCount "56" @default.
- W2240641835 countsByYear W22406418352016 @default.
- W2240641835 countsByYear W22406418352017 @default.
- W2240641835 countsByYear W22406418352018 @default.
- W2240641835 countsByYear W22406418352019 @default.
- W2240641835 countsByYear W22406418352020 @default.
- W2240641835 countsByYear W22406418352021 @default.
- W2240641835 countsByYear W22406418352022 @default.
- W2240641835 countsByYear W22406418352023 @default.
- W2240641835 crossrefType "journal-article" @default.
- W2240641835 hasAuthorship W2240641835A5007918498 @default.
- W2240641835 hasAuthorship W2240641835A5027907338 @default.
- W2240641835 hasAuthorship W2240641835A5029023520 @default.
- W2240641835 hasAuthorship W2240641835A5035745788 @default.
- W2240641835 hasBestOaLocation W22406418352 @default.
- W2240641835 hasConcept C104317684 @default.
- W2240641835 hasConcept C106131492 @default.
- W2240641835 hasConcept C152139883 @default.
- W2240641835 hasConcept C153180895 @default.
- W2240641835 hasConcept C154945302 @default.
- W2240641835 hasConcept C165696696 @default.
- W2240641835 hasConcept C185592680 @default.
- W2240641835 hasConcept C197129107 @default.
- W2240641835 hasConcept C204201278 @default.
- W2240641835 hasConcept C23123220 @default.
- W2240641835 hasConcept C28490314 @default.
- W2240641835 hasConcept C31972630 @default.
- W2240641835 hasConcept C33954974 @default.
- W2240641835 hasConcept C38652104 @default.
- W2240641835 hasConcept C40969351 @default.
- W2240641835 hasConcept C41008148 @default.
- W2240641835 hasConcept C50644808 @default.
- W2240641835 hasConcept C52622490 @default.
- W2240641835 hasConcept C55493867 @default.
- W2240641835 hasConcept C61328038 @default.
- W2240641835 hasConcept C63479239 @default.
- W2240641835 hasConcept C95623464 @default.
- W2240641835 hasConceptScore W2240641835C104317684 @default.
- W2240641835 hasConceptScore W2240641835C106131492 @default.
- W2240641835 hasConceptScore W2240641835C152139883 @default.
- W2240641835 hasConceptScore W2240641835C153180895 @default.
- W2240641835 hasConceptScore W2240641835C154945302 @default.
- W2240641835 hasConceptScore W2240641835C165696696 @default.
- W2240641835 hasConceptScore W2240641835C185592680 @default.
- W2240641835 hasConceptScore W2240641835C197129107 @default.
- W2240641835 hasConceptScore W2240641835C204201278 @default.
- W2240641835 hasConceptScore W2240641835C23123220 @default.
- W2240641835 hasConceptScore W2240641835C28490314 @default.