About: Fitting class-based language models into weighted finite-state transducer framework     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
  • In our paper we propose a general way of incorporating class-based language models with many-to-many word-to-class mapping into the finite-state transducer (FST) framework. Since class-based models alone usually do not improve the recognition accuracy , we also present a method for an efficient language model combination. An example of a word-to-class mapping based on morphological tags is also given. Several word-based and tag-based language models are tested in the task of transcribing Czech b roadcast news. Results show that class-based models help to achieve a moderate improvement in recognition accuracy.
  • In our paper we propose a general way of incorporating class-based language models with many-to-many word-to-class mapping into the finite-state transducer (FST) framework. Since class-based models alone usually do not improve the recognition accuracy , we also present a method for an efficient language model combination. An example of a word-to-class mapping based on morphological tags is also given. Several word-based and tag-based language models are tested in the task of transcribing Czech b roadcast news. Results show that class-based models help to achieve a moderate improvement in recognition accuracy. (en)
Title
  • Fitting class-based language models into weighted finite-state transducer framework
  • Fitting class-based language models into weighted finite-state transducer framework (en)
skos:prefLabel
  • Fitting class-based language models into weighted finite-state transducer framework
  • Fitting class-based language models into weighted finite-state transducer framework (en)
skos:notation
  • RIV/49777513:23520/03:00000158!RIV/2004/MSM/235204/N
http://linked.open.../vavai/riv/strany
  • 1873-1876
http://linked.open...avai/riv/aktivita
http://linked.open...avai/riv/aktivity
  • P(LN00A063)
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
  • 607414
http://linked.open...ai/riv/idVysledku
  • RIV/49777513:23520/03:00000158
http://linked.open...riv/jazykVysledku
http://linked.open.../riv/klicovaSlova
  • language modeling;finite-state automata;speech recognition (en)
http://linked.open.../riv/klicoveSlovo
http://linked.open...ontrolniKodProRIV
  • [C70B35F71F27]
http://linked.open...v/mistoKonaniAkce
  • Geneva
http://linked.open...i/riv/mistoVydani
  • Geneva
http://linked.open...i/riv/nazevZdroje
  • EUROSPEECH 2003 PROCEEDINGS
http://linked.open...in/vavai/riv/obor
http://linked.open...ichTvurcuVysledku
http://linked.open...cetTvurcuVysledku
http://linked.open...ocetUcastnikuAkce
http://linked.open...nichUcastnikuAkce
http://linked.open...vavai/riv/projekt
http://linked.open...UplatneniVysledku
http://linked.open...iv/tvurceVysledku
  • Ircing, Pavel
  • Psutka, Josef
http://linked.open...vavai/riv/typAkce
http://linked.open.../riv/zahajeniAkce
number of pages
http://purl.org/ne...btex#hasPublisher
  • ISCA
http://localhost/t...ganizacniJednotka
  • 23520
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, 78 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software