Matches in SemOpenAlex for { <https://semopenalex.org/work/W1515103638> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W1515103638 abstract "Statistical classifiers operate on features that generally include both useful and useless information. These two types of information are difficult to separate in the feature domain. Recently, a new paradigm based on a Latent Factor Analysis (LFA) proposed a model decomposition into usefull and useless components. This method was successfully applied to speaker and language recognition tasks. In this paper, we study the use of LFA for video genre classification by using only the audio channel. We propose a classification method based on short-term cep-stral features and Gaussian Mixture Models (GMM) or Support Vector Machine (SVM) classifiers, that are combined with Factor Analysis (FA). Experiments are conducted on a corpus composed of 5 types of video (musics, commercials, cartoons, movies and news). The relative classification error reduction obtained by using the best factor analysis configuration with respect to the baseline system, Gaussian Mixture Model Universal Background Model (GMM-UBM), is about 56%, corresponding to a correct identification rate of about 90%." @default.
- W1515103638 created "2016-06-24" @default.
- W1515103638 creator A5017334281 @default.
- W1515103638 creator A5050508708 @default.
- W1515103638 creator A5071001941 @default.
- W1515103638 date "2009-09-06" @default.
- W1515103638 modified "2023-09-26" @default.
- W1515103638 title "Factor analysis for audio-based video genre classification" @default.
- W1515103638 cites W1563750459 @default.
- W1515103638 cites W2022035644 @default.
- W1515103638 cites W2097470427 @default.
- W1515103638 cites W2100454127 @default.
- W1515103638 cites W2100969003 @default.
- W1515103638 cites W2113144451 @default.
- W1515103638 cites W2121415728 @default.
- W1515103638 cites W2121750345 @default.
- W1515103638 cites W2142526407 @default.
- W1515103638 cites W2147147599 @default.
- W1515103638 cites W2151920764 @default.
- W1515103638 cites W2904424563 @default.
- W1515103638 cites W32979931 @default.
- W1515103638 doi "https://doi.org/10.21437/interspeech.2009-336" @default.
- W1515103638 hasPublicationYear "2009" @default.
- W1515103638 type Work @default.
- W1515103638 sameAs 1515103638 @default.
- W1515103638 citedByCount "7" @default.
- W1515103638 countsByYear W15151036382014 @default.
- W1515103638 countsByYear W15151036382019 @default.
- W1515103638 crossrefType "proceedings-article" @default.
- W1515103638 hasAuthorship W1515103638A5017334281 @default.
- W1515103638 hasAuthorship W1515103638A5050508708 @default.
- W1515103638 hasAuthorship W1515103638A5071001941 @default.
- W1515103638 hasConcept C12267149 @default.
- W1515103638 hasConcept C138885662 @default.
- W1515103638 hasConcept C153180895 @default.
- W1515103638 hasConcept C154945302 @default.
- W1515103638 hasConcept C199360897 @default.
- W1515103638 hasConcept C204321447 @default.
- W1515103638 hasConcept C2776401178 @default.
- W1515103638 hasConcept C2781039887 @default.
- W1515103638 hasConcept C28490314 @default.
- W1515103638 hasConcept C40969351 @default.
- W1515103638 hasConcept C41008148 @default.
- W1515103638 hasConcept C41895202 @default.
- W1515103638 hasConcept C52622490 @default.
- W1515103638 hasConcept C61224824 @default.
- W1515103638 hasConcept C83665646 @default.
- W1515103638 hasConceptScore W1515103638C12267149 @default.
- W1515103638 hasConceptScore W1515103638C138885662 @default.
- W1515103638 hasConceptScore W1515103638C153180895 @default.
- W1515103638 hasConceptScore W1515103638C154945302 @default.
- W1515103638 hasConceptScore W1515103638C199360897 @default.
- W1515103638 hasConceptScore W1515103638C204321447 @default.
- W1515103638 hasConceptScore W1515103638C2776401178 @default.
- W1515103638 hasConceptScore W1515103638C2781039887 @default.
- W1515103638 hasConceptScore W1515103638C28490314 @default.
- W1515103638 hasConceptScore W1515103638C40969351 @default.
- W1515103638 hasConceptScore W1515103638C41008148 @default.
- W1515103638 hasConceptScore W1515103638C41895202 @default.
- W1515103638 hasConceptScore W1515103638C52622490 @default.
- W1515103638 hasConceptScore W1515103638C61224824 @default.
- W1515103638 hasConceptScore W1515103638C83665646 @default.
- W1515103638 hasLocation W15151036381 @default.
- W1515103638 hasOpenAccess W1515103638 @default.
- W1515103638 hasPrimaryLocation W15151036381 @default.
- W1515103638 hasRelatedWork W1503543100 @default.
- W1515103638 hasRelatedWork W1571425261 @default.
- W1515103638 hasRelatedWork W1653228644 @default.
- W1515103638 hasRelatedWork W1969347722 @default.
- W1515103638 hasRelatedWork W1990822289 @default.
- W1515103638 hasRelatedWork W2009169628 @default.
- W1515103638 hasRelatedWork W2009292852 @default.
- W1515103638 hasRelatedWork W2053236680 @default.
- W1515103638 hasRelatedWork W2065342515 @default.
- W1515103638 hasRelatedWork W2100700860 @default.
- W1515103638 hasRelatedWork W2104619451 @default.
- W1515103638 hasRelatedWork W2122706618 @default.
- W1515103638 hasRelatedWork W2127738412 @default.
- W1515103638 hasRelatedWork W2130386239 @default.
- W1515103638 hasRelatedWork W2160149277 @default.
- W1515103638 hasRelatedWork W2377398665 @default.
- W1515103638 hasRelatedWork W2390789328 @default.
- W1515103638 hasRelatedWork W2610528887 @default.
- W1515103638 hasRelatedWork W268756429 @default.
- W1515103638 hasRelatedWork W2854809490 @default.
- W1515103638 isParatext "false" @default.
- W1515103638 isRetracted "false" @default.
- W1515103638 magId "1515103638" @default.
- W1515103638 workType "article" @default.