This HTML5 document contains 45 embedded RDF statements represented using HTML+Microdata notation.

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

Namespace Prefixes

PrefixIRI
n5http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n9http://purl.org/net/nknouf/ns/bibtex#
n3http://localhost/temp/predkladatel/
n18http://linked.opendata.cz/resource/domain/vavai/projekt/
n8http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n20http://linked.opendata.cz/resource/domain/vavai/subjekt/
n19http://linked.opendata.cz/ontology/domain/vavai/
n11https://schema.org/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n15http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F49777513%3A23520%2F13%3A43920612%21RIV14-TA0-23520___/
rdfshttp://www.w3.org/2000/01/rdf-schema#
n4http://linked.opendata.cz/ontology/domain/vavai/riv/
n17http://bibframe.org/vocab/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n14http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n24http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n22http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n16http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n21http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n13http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n10http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F49777513%3A23520%2F13%3A43920612%21RIV14-TA0-23520___
rdf:type
n19:Vysledek skos:Concept
rdfs:seeAlso
http://link.springer.com/chapter/10.1007/978-3-319-01931-4_14
dcterms:description
Probabilistic Linear Discriminant Analysis (PLDA) and the concept of i-vectors are state-of-the-art methods used in the speaker recognition. They are based on Factor Analysis, in which a data covariance matrix is decomposed in order to find a low dimensional representation of given feature vectors. More precisely, the Factor Analysis based methods seek for directions/subspaces in which the projected (overall/between/within) variance is highest. In order to train models related to individual methods, development speech corpora comprising various acoustic conditions are utilized. The higher are the variations in some of these acoustic conditions, the more will the model tend to reflect them. Strong data variations in some of the development corpora may suppress conditions present in other corpora. This can lead to poor recognition when acoustic variations in test conditions significantly differ. In this paper techniques alleviating such effects are investigated. The idea is to use several background and i-vector models related to different parts of development data so that several i-vectors are extracted, processed and handed over to the PLDA modelling. PLDA model is then used to utilize all the extracted information and provide the verification result. Probabilistic Linear Discriminant Analysis (PLDA) and the concept of i-vectors are state-of-the-art methods used in the speaker recognition. They are based on Factor Analysis, in which a data covariance matrix is decomposed in order to find a low dimensional representation of given feature vectors. More precisely, the Factor Analysis based methods seek for directions/subspaces in which the projected (overall/between/within) variance is highest. In order to train models related to individual methods, development speech corpora comprising various acoustic conditions are utilized. The higher are the variations in some of these acoustic conditions, the more will the model tend to reflect them. Strong data variations in some of the development corpora may suppress conditions present in other corpora. This can lead to poor recognition when acoustic variations in test conditions significantly differ. In this paper techniques alleviating such effects are investigated. The idea is to use several background and i-vector models related to different parts of development data so that several i-vectors are extracted, processed and handed over to the PLDA modelling. PLDA model is then used to utilize all the extracted information and provide the verification result.
dcterms:title
Dealing with Diverse Data Variances in Factor Analysis Based Methods Dealing with Diverse Data Variances in Factor Analysis Based Methods
skos:prefLabel
Dealing with Diverse Data Variances in Factor Analysis Based Methods Dealing with Diverse Data Variances in Factor Analysis Based Methods
skos:notation
RIV/49777513:23520/13:43920612!RIV14-TA0-23520___
n19:predkladatel
n20:orjk%3A23520
n4:aktivita
n22:P
n4:aktivity
P(TA01030476)
n4:dodaniDat
n10:2014
n4:domaciTvurceVysledku
n8:8612889
n4:druhVysledku
n13:D
n4:duvernostUdaju
n24:S
n4:entitaPredkladatele
n15:predkladatel
n4:idSjednocenehoVysledku
68058
n4:idVysledku
RIV/49777513:23520/13:43920612
n4:jazykVysledku
n16:eng
n4:klicovaSlova
speaker recognition, PLDA, i-vector, factor analysis, decomposition
n4:klicoveSlovo
n14:factor%20analysis n14:speaker%20recognition n14:i-vector n14:decomposition n14:PLDA
n4:kontrolniKodProRIV
[8EDE1A210005]
n4:mistoKonaniAkce
Pilsen, Czech Republic
n4:mistoVydani
Cham
n4:nazevZdroje
Speech and Computer
n4:obor
n21:JD
n4:pocetDomacichTvurcuVysledku
1
n4:pocetTvurcuVysledku
1
n4:projekt
n18:TA01030476
n4:rokUplatneniVysledku
n10:2013
n4:tvurceVysledku
Machlica, Lukáš
n4:typAkce
n5:WRD
n4:zahajeniAkce
2013-09-01+02:00
s:issn
0302-9743
s:numberOfPages
8
n17:doi
10.1007/978-3-319-01931-4_14
n9:hasPublisher
Springer-Verlag
n11:isbn
978-3-319-01930-7
n3:organizacniJednotka
23520