About: Feature And Score Level Combination Of Subspace Gaussians In LVCSR Task     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
  • We have demonstrated that the SGMM framework is an efficient approach in the LVCSR task. Overall evaluations of SGMMs exploiting powerful but complex PLP-BN features yield similar results as those obtained by conventional HMM/GMMs. Nevertheless, the total number of SGMM parameters is about 3 times less than in the HMM/GMM framework. Evaluation results also indicate different properties of the examined acoustic modeling techniques. Although SGMMs consistently outperform HMM/GMMs when built over individual features, HMM/GMMs can benefit much more from the feature-level combination than SGMMs. Nevertheless based on an analysis measuring complementarity of individual recognition systems, we show that SGMM-based recognizers produce heterogeneous outputs (scores) and thus subsequent score-level combination can bring additional improvement.
  • We have demonstrated that the SGMM framework is an efficient approach in the LVCSR task. Overall evaluations of SGMMs exploiting powerful but complex PLP-BN features yield similar results as those obtained by conventional HMM/GMMs. Nevertheless, the total number of SGMM parameters is about 3 times less than in the HMM/GMM framework. Evaluation results also indicate different properties of the examined acoustic modeling techniques. Although SGMMs consistently outperform HMM/GMMs when built over individual features, HMM/GMMs can benefit much more from the feature-level combination than SGMMs. Nevertheless based on an analysis measuring complementarity of individual recognition systems, we show that SGMM-based recognizers produce heterogeneous outputs (scores) and thus subsequent score-level combination can bring additional improvement. (en)
Title
  • Feature And Score Level Combination Of Subspace Gaussians In LVCSR Task
  • Feature And Score Level Combination Of Subspace Gaussians In LVCSR Task (en)
skos:prefLabel
  • Feature And Score Level Combination Of Subspace Gaussians In LVCSR Task
  • Feature And Score Level Combination Of Subspace Gaussians In LVCSR Task (en)
skos:notation
  • RIV/00216305:26230/13:PU106379!RIV14-GA0-26230___
http://linked.open...avai/predkladatel
http://linked.open...avai/riv/aktivita
http://linked.open...avai/riv/aktivity
  • P(GPP202/12/P604)
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
  • 74797
http://linked.open...ai/riv/idVysledku
  • RIV/00216305:26230/13:PU106379
http://linked.open...riv/jazykVysledku
http://linked.open.../riv/klicovaSlova
  • Automatic Speech Recognition, Discriminative features, System combination (en)
http://linked.open.../riv/klicoveSlovo
http://linked.open...ontrolniKodProRIV
  • [AB159AF90E76]
http://linked.open...v/mistoKonaniAkce
  • Vancouver
http://linked.open...i/riv/mistoVydani
  • Vancouver
http://linked.open...i/riv/nazevZdroje
  • Proceedings of ICASSP 2013
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...iv/tvurceVysledku
  • Karafiát, Martin
  • Povey, Daniel
  • Motlíček, Petr
http://linked.open...vavai/riv/typAkce
http://linked.open.../riv/zahajeniAkce
number of pages
http://purl.org/ne...btex#hasPublisher
  • IEEE Signal Processing Society
https://schema.org/isbn
  • 978-1-4799-0355-9
http://localhost/t...ganizacniJednotka
  • 26230
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, 58 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software