Matches in SemOpenAlex for { <https://semopenalex.org/work/W2054971567> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W2054971567 endingPage "63" @default.
- W2054971567 startingPage "47" @default.
- W2054971567 abstract "This article describes a new Speaker Discrimination System (SDS), which is a part of an overall project called Audio Documents Indexing based on a Speaker Discrimination System (ADISDS). Speaker discrimination consists in checking whether two speech segments come from the same speaker or not. This research domain presents an important field in biometry, since the voice remains an important feature used at distance (via telephone). However, although some discriminative classifiers do exist nowadays, their performances are not enough sufficient for short speech segments. This issue led us to propose an efficient fusion between such classifiers in order to enhance the discriminative performance. This fusion is obtained, by using three different techniques: a serial fusion, parallel fusion and serial-parallel fusion. Also, two classifiers have been chosen for the evaluation: a mono-gaussian statistical classifier and a Multi Layer Perceptron (MLP). Several experiments of speaker discrimination are conducted on different databases: Hub4 Broadcast-News and telephonic calls. Results show that the fusion has efficiently improved the scores obtained by each approach alone. So, for instance, we got an Equal Error Rate (EER) of about 7% on a subset of Hub4 Broadcast-News database, with short segments of 4 seconds, and an EER of about 4% on telephonic speech, with medium segments of 10 seconds." @default.
- W2054971567 created "2016-06-24" @default.
- W2054971567 creator A5006433433 @default.
- W2054971567 creator A5025214147 @default.
- W2054971567 date "2009-10-01" @default.
- W2054971567 modified "2023-09-24" @default.
- W2054971567 title "Speaker Discrimination on Broadcast News and Telephonic Calls Using a Fusion of Neural and Statistical Classifiers" @default.
- W2054971567 cites W105018361 @default.
- W2054971567 cites W1550755746 @default.
- W2054971567 cites W1979463116 @default.
- W2054971567 cites W2001954572 @default.
- W2054971567 cites W2043741310 @default.
- W2054971567 cites W2069883713 @default.
- W2054971567 cites W2069976350 @default.
- W2054971567 cites W2094225911 @default.
- W2054971567 cites W2130039513 @default.
- W2054971567 cites W2140959843 @default.
- W2054971567 cites W2145399779 @default.
- W2054971567 cites W2145929752 @default.
- W2054971567 cites W2165880886 @default.
- W2054971567 cites W2167075312 @default.
- W2054971567 cites W2168866939 @default.
- W2054971567 cites W339880525 @default.
- W2054971567 doi "https://doi.org/10.4018/jmcmc.2009072804" @default.
- W2054971567 hasPublicationYear "2009" @default.
- W2054971567 type Work @default.
- W2054971567 sameAs 2054971567 @default.
- W2054971567 citedByCount "2" @default.
- W2054971567 crossrefType "journal-article" @default.
- W2054971567 hasAuthorship W2054971567A5006433433 @default.
- W2054971567 hasAuthorship W2054971567A5025214147 @default.
- W2054971567 hasConcept C133892786 @default.
- W2054971567 hasConcept C138885662 @default.
- W2054971567 hasConcept C149838564 @default.
- W2054971567 hasConcept C153180895 @default.
- W2054971567 hasConcept C154945302 @default.
- W2054971567 hasConcept C158525013 @default.
- W2054971567 hasConcept C28490314 @default.
- W2054971567 hasConcept C40969351 @default.
- W2054971567 hasConcept C41008148 @default.
- W2054971567 hasConcept C41895202 @default.
- W2054971567 hasConcept C50644808 @default.
- W2054971567 hasConcept C60908668 @default.
- W2054971567 hasConcept C95623464 @default.
- W2054971567 hasConcept C97931131 @default.
- W2054971567 hasConceptScore W2054971567C133892786 @default.
- W2054971567 hasConceptScore W2054971567C138885662 @default.
- W2054971567 hasConceptScore W2054971567C149838564 @default.
- W2054971567 hasConceptScore W2054971567C153180895 @default.
- W2054971567 hasConceptScore W2054971567C154945302 @default.
- W2054971567 hasConceptScore W2054971567C158525013 @default.
- W2054971567 hasConceptScore W2054971567C28490314 @default.
- W2054971567 hasConceptScore W2054971567C40969351 @default.
- W2054971567 hasConceptScore W2054971567C41008148 @default.
- W2054971567 hasConceptScore W2054971567C41895202 @default.
- W2054971567 hasConceptScore W2054971567C50644808 @default.
- W2054971567 hasConceptScore W2054971567C60908668 @default.
- W2054971567 hasConceptScore W2054971567C95623464 @default.
- W2054971567 hasConceptScore W2054971567C97931131 @default.
- W2054971567 hasIssue "4" @default.
- W2054971567 hasLocation W20549715671 @default.
- W2054971567 hasOpenAccess W2054971567 @default.
- W2054971567 hasPrimaryLocation W20549715671 @default.
- W2054971567 hasRelatedWork W1979732085 @default.
- W2054971567 hasRelatedWork W1981185131 @default.
- W2054971567 hasRelatedWork W2003380312 @default.
- W2054971567 hasRelatedWork W2020437063 @default.
- W2054971567 hasRelatedWork W2103897043 @default.
- W2054971567 hasRelatedWork W2114541077 @default.
- W2054971567 hasRelatedWork W2982817420 @default.
- W2054971567 hasRelatedWork W3148366653 @default.
- W2054971567 hasRelatedWork W4288029399 @default.
- W2054971567 hasRelatedWork W2288288340 @default.
- W2054971567 hasVolume "1" @default.
- W2054971567 isParatext "false" @default.
- W2054971567 isRetracted "false" @default.
- W2054971567 magId "2054971567" @default.
- W2054971567 workType "article" @default.