This HTML5 document contains 49 embedded RDF statements represented using HTML+Microdata notation.

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

Namespace Prefixes

PrefixIRI
n16http://linked.opendata.cz/ontology/domain/vavai/riv/typAkce/
dctermshttp://purl.org/dc/terms/
n22http://localhost/temp/predkladatel/
n7http://purl.org/net/nknouf/ns/bibtex#
n18http://linked.opendata.cz/resource/domain/vavai/riv/tvurce/
n10http://linked.opendata.cz/resource/domain/vavai/projekt/
n17http://linked.opendata.cz/ontology/domain/vavai/
n15https://schema.org/
n13http://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/
n6http://linked.opendata.cz/resource/domain/vavai/vysledek/RIV%2F49777513%3A23520%2F03%3A00000160%21RIV%2F2004%2FMSM%2F235204%2FN/
n2http://linked.opendata.cz/resource/domain/vavai/vysledek/
rdfhttp://www.w3.org/1999/02/22-rdf-syntax-ns#
n4http://linked.opendata.cz/ontology/domain/vavai/riv/klicoveSlovo/
n14http://linked.opendata.cz/ontology/domain/vavai/riv/duvernostUdaju/
xsdhhttp://www.w3.org/2001/XMLSchema#
n19http://linked.opendata.cz/ontology/domain/vavai/riv/jazykVysledku/
n12http://linked.opendata.cz/ontology/domain/vavai/riv/aktivita/
n21http://linked.opendata.cz/ontology/domain/vavai/riv/druhVysledku/
n20http://linked.opendata.cz/ontology/domain/vavai/riv/obor/
n8http://reference.data.gov.uk/id/gregorian-year/

Statements

Subject Item
n2:RIV%2F49777513%3A23520%2F03%3A00000160%21RIV%2F2004%2FMSM%2F235204%2FN
rdf:type
skos:Concept n17:Vysledek
dcterms:description
Automatic recognition of a TV commentary accompanying an ice-hockey match is usually a hard task due to the spontaneous speech of a commentator put often into a very loud background noise. Although a vocabulary of an ice-hockey commentary seems to be re latively well limited we show that the lexicon formed by collecting words of 15 ice hockey matches provided by one TV commentator does not sufficiently cover commen- taries of new matches and a high OOV (Out Of Vocabulary) rate brings about many recogni tion problems. To partly alleviate this problem we collected manual transcripts of further 16 matches and designed a knowledge-base adaptation technique ensuring an efficient modification of a recognition lexicon and LM statistics. A suitable adaptation approach was also tested with a goal of adapting a LM to a style of speaking of a new commentator. Automatic recognition of a TV commentary accompanying an ice-hockey match is usually a hard task due to the spontaneous speech of a commentator put often into a very loud background noise. Although a vocabulary of an ice-hockey commentary seems to be re latively well limited we show that the lexicon formed by collecting words of 15 ice hockey matches provided by one TV commentator does not sufficiently cover commen- taries of new matches and a high OOV (Out Of Vocabulary) rate brings about many recogni tion problems. To partly alleviate this problem we collected manual transcripts of further 16 matches and designed a knowledge-base adaptation technique ensuring an efficient modification of a recognition lexicon and LM statistics. A suitable adaptation approach was also tested with a goal of adapting a LM to a style of speaking of a new commentator.
dcterms:title
Automatic transcription of TV ice-hockey commentary Automatic transcription of TV ice-hockey commentary
skos:prefLabel
Automatic transcription of TV ice-hockey commentary Automatic transcription of TV ice-hockey commentary
skos:notation
RIV/49777513:23520/03:00000160!RIV/2004/MSM/235204/N
n3:strany
419-423
n3:aktivita
n12:Z n12:P
n3:aktivity
P(LN00A063), Z(MSM 235200004)
n3:dodaniDat
n8:2004
n3:domaciTvurceVysledku
n18:4396855 n18:4979222 n18:6579760
n3:druhVysledku
n21:D
n3:duvernostUdaju
n14:S
n3:entitaPredkladatele
n6:predkladatel
n3:idSjednocenehoVysledku
599359
n3:idVysledku
RIV/49777513:23520/03:00000160
n3:jazykVysledku
n19:eng
n3:klicovaSlova
continuous speech recognition;corpus collection;class-based language model;spontaneous speech
n3:klicoveSlovo
n4:class-based%20language%20model n4:spontaneous%20speech n4:continuous%20speech%20recognition n4:corpus%20collection
n3:kontrolniKodProRIV
[C618B23A293A]
n3:mistoKonaniAkce
Orlando
n3:mistoVydani
Orlando
n3:nazevZdroje
Proceedings
n3:obor
n20:JD
n3:pocetDomacichTvurcuVysledku
3
n3:pocetTvurcuVysledku
4
n3:pocetUcastnikuAkce
0
n3:pocetZahranicnichUcastnikuAkce
0
n3:projekt
n10:LN00A063
n3:rokUplatneniVysledku
n8:2003
n3:tvurceVysledku
Ircing, Pavel Hoidekr, Jan Psutka, Josef
n3:typAkce
n16:WRD
n3:zahajeniAkce
2003-07-27+02:00
n3:zamer
n13:MSM%20235200004
s:numberOfPages
5
n7:hasPublisher
International Institute of Informatics and Systemics
n15:isbn
980-6560-01-9
n22:organizacniJednotka
23520