About: MAP Based Speaker Adaptation in Very Large Vocabulary Speech Recognition of Czech     Goto   Sponge   NotDistinct   Permalink

An Entity of Type : http://linked.opendata.cz/ontology/domain/vavai/Vysledek, within Data Space : linked.opendata.cz associated with source document(s)

AttributesValues
rdf:type
Description
  • Proposed speaker adaptation methods leaded to reduction of error rate in isolated-word recognition by 20% or even 35% if the speaker provided 10 or 100 adaptation words, respectively.In the more complex task of continuous speech recognition, the WER was be reduced by 20% when 100 sentences were used for adaptation.
  • Proposed speaker adaptation methods leaded to reduction of error rate in isolated-word recognition by 20% or even 35% if the speaker provided 10 or 100 adaptation words, respectively.In the more complex task of continuous speech recognition, the WER was be reduced by 20% when 100 sentences were used for adaptation. (en)
  • Navržené metody adaptace na mluvčího odvozené od metody MAP vedly ke snížení chybovosti systému rozpoznávání izolovaných slov relativně o 20% až 30%, když daný mluvčí poskytl 10 respektive 100 adaptačních slov.Ve složitější úloze rozpoznávání spojité řeči došlo v případě, že daný mluvčí namluvil 100 vět, ke zlepšení relativně o 20%. (cs)
Title
  • Adaptace na mluvčího založená na metodě MAP v systémech rozpoznávání řeči s velmi velkým slovníkem (cs)
  • MAP Based Speaker Adaptation in Very Large Vocabulary Speech Recognition of Czech
  • MAP Based Speaker Adaptation in Very Large Vocabulary Speech Recognition of Czech (en)
skos:prefLabel
  • Adaptace na mluvčího založená na metodě MAP v systémech rozpoznávání řeči s velmi velkým slovníkem (cs)
  • MAP Based Speaker Adaptation in Very Large Vocabulary Speech Recognition of Czech
  • MAP Based Speaker Adaptation in Very Large Vocabulary Speech Recognition of Czech (en)
skos:notation
  • RIV/46747885:24220/04:00000110!RIV/2005/GA0/242205/N
http://linked.open.../vavai/riv/strany
  • 42-46
http://linked.open...avai/riv/aktivita
http://linked.open...avai/riv/aktivity
  • P(GA102/02/0124), Z(MSM 242200001)
http://linked.open...iv/cisloPeriodika
  • 3
http://linked.open...vai/riv/dodaniDat
http://linked.open...aciTvurceVysledku
http://linked.open.../riv/druhVysledku
http://linked.open...iv/duvernostUdaju
http://linked.open...titaPredkladatele
http://linked.open...dnocenehoVysledku
  • 572249
http://linked.open...ai/riv/idVysledku
  • RIV/46747885:24220/04:00000110
http://linked.open...riv/jazykVysledku
http://linked.open.../riv/klicovaSlova
  • %22speaker adaptation;speech recognition%22 (en)
http://linked.open.../riv/klicoveSlovo
http://linked.open...odStatuVydavatele
  • CZ - Česká republika
http://linked.open...ontrolniKodProRIV
  • [9C0E1A187019]
http://linked.open...i/riv/nazevZdroje
  • Radioengineering
http://linked.open...in/vavai/riv/obor
http://linked.open...ichTvurcuVysledku
http://linked.open...cetTvurcuVysledku
http://linked.open...vavai/riv/projekt
http://linked.open...UplatneniVysledku
http://linked.open...v/svazekPeriodika
  • 13
http://linked.open...iv/tvurceVysledku
  • Nouza, Jan
  • Červa, Petr
http://linked.open...n/vavai/riv/zamer
issn
  • 1210-2512
number of pages
http://localhost/t...ganizacniJednotka
  • 24220
Faceted Search & Find service v1.16.118 as of Jun 21 2024


Alternative Linked Data Documents: ODE     Content Formats:   [cxml] [csv]     RDF   [text] [turtle] [ld+json] [rdf+json] [rdf+xml]     ODATA   [atom+xml] [odata+json]     Microdata   [microdata+json] [html]    About   
This material is Open Knowledge   W3C Semantic Web Technology [RDF Data] Valid XHTML + RDFa
OpenLink Virtuoso version 07.20.3240 as of Jun 21 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 85 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software