About: A Direct Criterion Minimization based fMLLR via Gradient Descend     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
rdfs:seeAlso
Description
  • Adaptation techniques are necessary in automatic speech recognizers to improve a recognition accuracy. Linear Transformation methods (MLLR or fMLLR) are the most favorite in the case of limited available data. The fMLLR is the feature-space transformation. This is the advantage with contrast to MLLR that transforms the entire acoustic model. The classical fMLLR estimation involves maximization of the likelihood criterion based on individual Gaussian components statistic.We proposed an approach which takes into account the overall likelihood of a HMM state. It estimates the transformation to optimize the ML criterion of HMM directly using gradient descent algorithm.
  • Adaptation techniques are necessary in automatic speech recognizers to improve a recognition accuracy. Linear Transformation methods (MLLR or fMLLR) are the most favorite in the case of limited available data. The fMLLR is the feature-space transformation. This is the advantage with contrast to MLLR that transforms the entire acoustic model. The classical fMLLR estimation involves maximization of the likelihood criterion based on individual Gaussian components statistic.We proposed an approach which takes into account the overall likelihood of a HMM state. It estimates the transformation to optimize the ML criterion of HMM directly using gradient descent algorithm. (en)
Title
  • A Direct Criterion Minimization based fMLLR via Gradient Descend
  • A Direct Criterion Minimization based fMLLR via Gradient Descend (en)
skos:prefLabel
  • A Direct Criterion Minimization based fMLLR via Gradient Descend
  • A Direct Criterion Minimization based fMLLR via Gradient Descend (en)
skos:notation
  • RIV/49777513:23520/13:43920629!RIV14-TA0-23520___
http://linked.open...avai/predkladatel
http://linked.open...avai/riv/aktivita
http://linked.open...avai/riv/aktivity
  • P(TA01030476)
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
  • 58586
http://linked.open...ai/riv/idVysledku
  • RIV/49777513:23520/13:43920629
http://linked.open...riv/jazykVysledku
http://linked.open.../riv/klicovaSlova
  • ASR, adaptation, fMLLR, gradient descend, Hessian matrix. (en)
http://linked.open.../riv/klicoveSlovo
http://linked.open...ontrolniKodProRIV
  • [FA98483EBE93]
http://linked.open...v/mistoKonaniAkce
  • Pilsen, Czech Republic
http://linked.open...i/riv/mistoVydani
  • Heidelberg
http://linked.open...i/riv/nazevZdroje
  • Text, Speech and Dialogue
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
  • Vaněk, Jan
  • Zajíc, Zbyněk
http://linked.open...vavai/riv/typAkce
http://linked.open.../riv/zahajeniAkce
issn
  • 0302-9743
number of pages
http://bibframe.org/vocab/doi
  • 10.1007/978-3-642-40585-3_8
http://purl.org/ne...btex#hasPublisher
  • Springer-Verlag
https://schema.org/isbn
  • 978-3-642-40584-6
http://localhost/t...ganizacniJednotka
  • 23520
Faceted Search & Find service v1.16.116 as of Feb 22 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 07.20.3239 as of Feb 22 2024, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (126 GB total memory, 80 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software