This HTML5 document contains 48 embedded RDF statements represented using HTML+Microdata notation.

The embedded RDF content will be recognized by any processor of HTML5 Microdata.

Namespace Prefixes

PrefixIRI
n9http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n16http://purl.org/net/nknouf/ns/bibtex#
n7http://localhost/temp/predkladatel/
n17http://linked.opendata.cz/resource/domain/vavai/projekt/
n6http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n14http://linked.opendata.cz/ontology/domain/vavai/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n3http://linked.opendata.cz/ontology/domain/vavai/riv/
n13http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F00216305%3A26230%2F09%3APU82688%21RIV10-MV0-26230___/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n11http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n10http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n20http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n8http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n19http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n18http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n15http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F00216305%3A26230%2F09%3APU82688%21RIV10-MV0-26230___
rdf:type
skos:Concept n14:Vysledek
dcterms:description
We propose a novel design for acoustic feature-based automatic spoken language recognizers. Our design is inspired by recent advances in text-independent speaker recognition, where intraclass variability is modeled by factor analysis in Gaussian mixture model (GMM) space. We use approximations to GMMlikelihoods which allow variable-length data sequences to be represented as statistics of fixed size. Our experiments on NIST LRE'07 show that variability-compensation of these statistics can reduce error-rates by a factor of three. Finally, we show that further improvements are possible with discriminative logistic regression training. We propose a novel design for acoustic feature-based automatic spoken language recognizers. Our design is inspired by recent advances in text-independent speaker recognition, where intraclass variability is modeled by factor analysis in Gaussian mixture model (GMM) space. We use approximations to GMMlikelihoods which allow variable-length data sequences to be represented as statistics of fixed size. Our experiments on NIST LRE'07 show that variability-compensation of these statistics can reduce error-rates by a factor of three. Finally, we show that further improvements are possible with discriminative logistic regression training.
dcterms:title
Discriminative Acoustic Language Recognition via Channel-Compensated GMM Statistics Discriminative Acoustic Language Recognition via Channel-Compensated GMM Statistics
skos:prefLabel
Discriminative Acoustic Language Recognition via Channel-Compensated GMM Statistics Discriminative Acoustic Language Recognition via Channel-Compensated GMM Statistics
skos:notation
RIV/00216305:26230/09:PU82688!RIV10-MV0-26230___
n3:aktivita
n8:P
n3:aktivity
P(GA102/08/0707), P(VD20072010B16)
n3:dodaniDat
n15:2010
n3:domaciTvurceVysledku
n6:7822995 n6:2912988 n6:4922514 Hubeika, Valiantsina
n3:druhVysledku
n18:D
n3:duvernostUdaju
n10:S
n3:entitaPredkladatele
n13:predkladatel
n3:idSjednocenehoVysledku
310723
n3:idVysledku
RIV/00216305:26230/09:PU82688
n3:jazykVysledku
n20:eng
n3:klicovaSlova
acoustic language recognition, intersession variability compensation, discriminative training
n3:klicoveSlovo
n11:discriminative%20training n11:acoustic%20language%20recognition n11:intersession%20variability%20compensation
n3:kontrolniKodProRIV
[882A74670C4F]
n3:mistoKonaniAkce
Brighton
n3:mistoVydani
Brighton
n3:nazevZdroje
Proc. Interspeech 2009
n3:obor
n19:JC
n3:pocetDomacichTvurcuVysledku
4
n3:pocetTvurcuVysledku
6
n3:projekt
n17:GA102%2F08%2F0707 n17:VD20072010B16
n3:rokUplatneniVysledku
n15:2009
n3:tvurceVysledku
Brümmer, Niko Burget, Lukáš Strasheim, Albeert Glembek, Ondřej Matějka, Pavel Hubeika, Valiantsina
n3:typAkce
n9:WRD
n3:zahajeniAkce
2009-09-06+02:00
s:issn
1990-9772
s:numberOfPages
4
n16:hasPublisher
International Speech Communication Association
n7:organizacniJednotka
26230