About: Robust Adaptation Techniques Dealing with Small Amount of Data

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

About: Robust Adaptation Techniques Dealing with Small Amount of Data 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://download.springer.com/static/pdf/237/chp%253A10.1007%252F978-3-642-32790-2_58.pdf?auth66=1352100308_6ca3feab5ab1f038650cd3b971c1f53b&ext=.pdf
Description	The worst problem the adaptation is dealing with is the lack of adaptation data. This work focuses on the feature Maximum Likelihood Linear Regression (fMLLR) adaptation where the number of free parameters to be estimated significantly decreases in comparison with other adaptation methods. However, the number of free parameters of fMLLR transform is still too high to be estimated properly when dealing with extremely small data sets. We described and compared various methods used to avoid this problem, namely the initialization of the fMLLR transform and a linear combination of basis matrices varying in the choice of the basis estimation (eigen decomposition, factor analysis, independent component analysis and maximum likelihood estimation). Initialization methods compensate the absence of the test speaker's data utilizing other suitable data. Methods using linear combination of basis matrices reduce the number of estimated fMLLR parameters to a smaller number of weights to be estimated. Experiments are aimed to compare results of proposed basis and initialization methods. The worst problem the adaptation is dealing with is the lack of adaptation data. This work focuses on the feature Maximum Likelihood Linear Regression (fMLLR) adaptation where the number of free parameters to be estimated significantly decreases in comparison with other adaptation methods. However, the number of free parameters of fMLLR transform is still too high to be estimated properly when dealing with extremely small data sets. We described and compared various methods used to avoid this problem, namely the initialization of the fMLLR transform and a linear combination of basis matrices varying in the choice of the basis estimation (eigen decomposition, factor analysis, independent component analysis and maximum likelihood estimation). Initialization methods compensate the absence of the test speaker's data utilizing other suitable data. Methods using linear combination of basis matrices reduce the number of estimated fMLLR parameters to a smaller number of weights to be estimated. Experiments are aimed to compare results of proposed basis and initialization methods. (en)
Title	Robust Adaptation Techniques Dealing with Small Amount of Data Robust Adaptation Techniques Dealing with Small Amount of Data (en)
skos:prefLabel	Robust Adaptation Techniques Dealing with Small Amount of Data Robust Adaptation Techniques Dealing with Small Amount of Data (en)
skos:notation	RIV/49777513:23520/12:43915990!RIV13-MK0-23520___
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(DF12P01OVV022)
http://linked.open...iv/cisloPeriodika	neuveden
http://linked.open...vai/riv/dodaniDat	2013
http://linked.open...aciTvurceVysledku	Zajíc, Zbyněk Müller, Luděk Machlica, Lukáš
http://linked.open.../riv/druhVysledku	J - Článek v odborném periodiku
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	165837
http://linked.open...ai/riv/idVysledku	RIV/49777513:23520/12:43915990
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	ASR, adaptation, fMLLR, robustness, initialization, basis (en)
http://linked.open.../riv/klicoveSlovo	initialization fMLLR basis adaptation robustness ASR
http://linked.open...odStatuVydavatele	DE - Spolková republika Německo
http://linked.open...ontrolniKodProRIV	[7F5B05249D7E]
http://linked.open...i/riv/nazevZdroje	Lecture Notes in Computer Science
http://linked.open...in/vavai/riv/obor	JD
http://linked.open...ichTvurcuVysledku	3 (xsd:int)
http://linked.open...cetTvurcuVysledku	3 (xsd:int)
http://linked.open...vavai/riv/projekt	ASR- and MT-based Access to a Large Archive of Cultural Heritage (AMALACH)
http://linked.open...UplatneniVysledku	2012
http://linked.open...v/svazekPeriodika	7499
http://linked.open...iv/tvurceVysledku	Machlica, Lukáš Zajíc, Zbyněk Müller, Luděk
issn	0302-9743
number of pages	8 (xsd:int)
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, 77 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software