About: Anti-Models: An Alternative Way to Discriminative Training

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: Anti-Models: An Alternative Way to Discriminative Training 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)

Attributes	Values
rdf:type	skos:Concept http://linked.opendata.cz/ontology/domain/vavai/Vysledek
rdfs:seeAlso	http://link.springer.com/chapter/10.1007/978-3-319-10816-2_54
Description	Traditional discriminative training methods modify Hidden Markov Model (HMM) parameters obtained via a Maximum Likelihood (ML) criterion based estimator. In this paper, anti-models are introduced instead. The anti-models are used in tandem with ML models to incorporate a discriminative information from training data set and modify the HMM output likelihood in a discriminative way. Traditional discriminative training methods are prone to over-fitting and require an extra stabilization. Also, convergence is not ensured and usually %22a proper%22 number of iterations is done. In the proposed anti-models concept, two parts, positive model and anti-model, are trained via ML criterion. Therefore, the convergence and the stability are ensured. Traditional discriminative training methods modify Hidden Markov Model (HMM) parameters obtained via a Maximum Likelihood (ML) criterion based estimator. In this paper, anti-models are introduced instead. The anti-models are used in tandem with ML models to incorporate a discriminative information from training data set and modify the HMM output likelihood in a discriminative way. Traditional discriminative training methods are prone to over-fitting and require an extra stabilization. Also, convergence is not ensured and usually %22a proper%22 number of iterations is done. In the proposed anti-models concept, two parts, positive model and anti-model, are trained via ML criterion. Therefore, the convergence and the stability are ensured. (en)
Title	Anti-Models: An Alternative Way to Discriminative Training Anti-Models: An Alternative Way to Discriminative Training (en)
skos:prefLabel	Anti-Models: An Alternative Way to Discriminative Training Anti-Models: An Alternative Way to Discriminative Training (en)
skos:notation	RIV/49777513:23520/14:43923104!RIV15-GA0-23520___
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(GBP103/12/G084)
http://linked.open...vai/riv/dodaniDat	2015
http://linked.open...aciTvurceVysledku	Vaněk, Jan Psutka, Josef
http://linked.open.../riv/druhVysledku	D - Článek ve sborníku
http://linked.open...iv/duvernostUdaju	S - Úplné a pravdivé údaje nepodléhající ochraně podle zvláštních právních předpisů
http://linked.open...titaPredkladatele	Západočeská univerzita v Plzni / Fakulta aplikovaných věd
http://linked.open...dnocenehoVysledku	3455
http://linked.open...ai/riv/idVysledku	RIV/49777513:23520/14:43923104
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	MPE; MCE; MMI; Anti-Models; Discriminative Training; Acoustic Modeling; HMM; ASR (en)
http://linked.open.../riv/klicoveSlovo	Discriminative Training HMM ASR MMI Acoustic Modeling Anti-Models MCE MPE
http://linked.open...ontrolniKodProRIV	[D055D6F6DA9A]
http://linked.open...v/mistoKonaniAkce	Brno, Czech Republic
http://linked.open...i/riv/mistoVydani	Heidelberg
http://linked.open...i/riv/nazevZdroje	Lecture Notes in Computer Science
http://linked.open...in/vavai/riv/obor	JD
http://linked.open...ichTvurcuVysledku	2 (xsd:int)
http://linked.open...cetTvurcuVysledku	2 (xsd:int)
http://linked.open...vavai/riv/projekt	Center for Large Scale Multi-modal Data Interpretation
http://linked.open...UplatneniVysledku	2014
http://linked.open...iv/tvurceVysledku	Psutka, Josef Vaněk, Jan
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open.../riv/zahajeniAkce	2014-09-08 (xsd:date)
issn	0302-9743
number of pages	8 (xsd:int)
http://bibframe.org/vocab/doi	10.1007/978-3-319-10816-2_54
http://purl.org/ne...btex#hasPublisher	Springer-Verlag
https://schema.org/isbn	978-3-319-10815-5
http://localhost/t...ganizacniJednotka	23520

Faceted Search & Find service v1.16.118 as of Jun 21 2024

Alternative Linked Data Documents: ODE Content Formats:

RDF

ODATA

Microdata

About

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, 75 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software