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
n18http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n11http://localhost/temp/predkladatel/
n8http://purl.org/net/nknouf/ns/bibtex#
n7http://linked.opendata.cz/resource/domain/vavai/projekt/
n4http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n20http://linked.opendata.cz/ontology/domain/vavai/
n17http://linked.opendata.cz/resource/domain/vavai/zamer/
shttp://schema.org/
skoshttp://www.w3.org/2004/02/skos/core#
n3http://linked.opendata.cz/ontology/domain/vavai/riv/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
n16http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F00216305%3A26230%2F08%3APU78050%21RIV10-MSM-26230___/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n9http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n15http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n19http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n13http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n21http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n6http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n14http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F00216305%3A26230%2F08%3APU78050%21RIV10-MSM-26230___
rdf:type
skos:Concept n20:Vysledek
dcterms:description
The amount of training data has a crucial effect on the accuracy of HMM based meeting recognition systems. One of the largest collections of speech data is conversational telephone speech which was found to match speech in meetings well. However it is naturally recorded with limited bandwidth. In previous work we presented a scheme that allows to transform wide-band meeting data into the same space for improved model training. In this paper we focused on integration of discriminative adaptation into this scheme. This integration is not straightforward and we present the complexity of this process. The models are tested on the NIST RT'05 meeting evaluation where a relative reduction in word error rate of 5.6% against non-adapted meeting system was achieved. The amount of training data has a crucial effect on the accuracy of HMM based meeting recognition systems. One of the largest collections of speech data is conversational telephone speech which was found to match speech in meetings well. However it is naturally recorded with limited bandwidth. In previous work we presented a scheme that allows to transform wide-band meeting data into the same space for improved model training. In this paper we focused on integration of discriminative adaptation into this scheme. This integration is not straightforward and we present the complexity of this process. The models are tested on the NIST RT'05 meeting evaluation where a relative reduction in word error rate of 5.6% against non-adapted meeting system was achieved.
dcterms:title
Discrimininative training of narrow band - wide band adaptated systems for meeting recognition Discrimininative training of narrow band - wide band adaptated systems for meeting recognition
skos:prefLabel
Discrimininative training of narrow band - wide band adaptated systems for meeting recognition Discrimininative training of narrow band - wide band adaptated systems for meeting recognition
skos:notation
RIV/00216305:26230/08:PU78050!RIV10-MSM-26230___
n3:aktivita
n13:P n13:Z
n3:aktivity
P(GA102/08/0707), P(GP102/06/P383), Z(MSM0021630528)
n3:dodaniDat
n14:2010
n3:domaciTvurceVysledku
n4:8912416 n4:8304874 n4:7822995
n3:druhVysledku
n21:D
n3:duvernostUdaju
n15:S
n3:entitaPredkladatele
n16:predkladatel
n3:idSjednocenehoVysledku
363780
n3:idVysledku
RIV/00216305:26230/08:PU78050
n3:jazykVysledku
n19:eng
n3:klicovaSlova
speech recognition<br>
n3:klicoveSlovo
n9:speech%20recognition%3Cbr%3E
n3:kontrolniKodProRIV
[79399523010C]
n3:mistoKonaniAkce
Brisbane, Australia
n3:mistoVydani
Brisbane
n3:nazevZdroje
Proc. Interspeech 2008
n3:obor
n6:JC
n3:pocetDomacichTvurcuVysledku
3
n3:pocetTvurcuVysledku
4
n3:projekt
n7:GA102%2F08%2F0707 n7:GP102%2F06%2FP383
n3:rokUplatneniVysledku
n14:2008
n3:tvurceVysledku
Černocký, Jan Hain, Thomas Karafiát, Martin Burget, Lukáš
n3:typAkce
n18:WRD
n3:zahajeniAkce
2008-09-22+02:00
n3:zamer
n17:MSM0021630528
s:issn
1990-9772
s:numberOfPages
4
n8:hasPublisher
International Speech Communication Association
n11:organizacniJednotka
26230