About: Convolutional Neural Network for Refinement of Speaker Adaptation Transformation

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

About: Convolutional Neural Network for Refinement of Speaker Adaptation Transformation 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/914/chp%253A10.1007%252F978-3-319-11581-8_20.pdf?auth66=1413288171_5b620d005701573765a4641007670c58&ext=.pdf
Description	The aim of this work is to propose a refinement of the shift-MLLR (shift Maximum Likelihood Linear Regression) adaptation of an acoustics model in the case of limited amount of adaptation data, which can lead to ill-conditioned transformations matrices. We try to suppress the influence of badly estimated transformation parameters utilizing the Artificial Neural Network (ANN), especially Convolutional Neural Network (CNN) with bottleneck layer on the end. The badly estimated shift-MLLR transformation is propagated through an ANN (suitably trained beforehand), and the output of the net is used as the new refined transformation. To train the ANN the well and the badly conditioned shift-MLLR transformations are used as outputs and inputs of ANN, respectively. The aim of this work is to propose a refinement of the shift-MLLR (shift Maximum Likelihood Linear Regression) adaptation of an acoustics model in the case of limited amount of adaptation data, which can lead to ill-conditioned transformations matrices. We try to suppress the influence of badly estimated transformation parameters utilizing the Artificial Neural Network (ANN), especially Convolutional Neural Network (CNN) with bottleneck layer on the end. The badly estimated shift-MLLR transformation is propagated through an ANN (suitably trained beforehand), and the output of the net is used as the new refined transformation. To train the ANN the well and the badly conditioned shift-MLLR transformations are used as outputs and inputs of ANN, respectively. (en)
Title	Convolutional Neural Network for Refinement of Speaker Adaptation Transformation Convolutional Neural Network for Refinement of Speaker Adaptation Transformation (en)
skos:prefLabel	Convolutional Neural Network for Refinement of Speaker Adaptation Transformation Convolutional Neural Network for Refinement of Speaker Adaptation Transformation (en)
skos:notation	RIV/49777513:23520/14:43922932!RIV15-MK0-23520___
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(DF12P01OVV022)
http://linked.open...vai/riv/dodaniDat	2015
http://linked.open...aciTvurceVysledku	Vaněk, Jan Zajíc, Zbyněk Müller, Luděk Zelinka, Jan
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	8917
http://linked.open...ai/riv/idVysledku	RIV/49777513:23520/14:43922932
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	ASR, Adaptation, shift-MLLR, ANN, CNN, bottleneck (en)
http://linked.open.../riv/klicoveSlovo	ANN bottleneck shift-MLLR ASR Adaptation CNN
http://linked.open...ontrolniKodProRIV	[767FFB9712F0]
http://linked.open...v/mistoKonaniAkce	Novi Sad, Serbia
http://linked.open...i/riv/mistoVydani	Heidelberg
http://linked.open...i/riv/nazevZdroje	Speech and Computer, 16th International Conference, SPECOM 2014, Novi Sad, Serbia, October 5-9, 2014, Proceedings
http://linked.open...in/vavai/riv/obor	JD
http://linked.open...ichTvurcuVysledku	4 (xsd:int)
http://linked.open...cetTvurcuVysledku	4 (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	2014
http://linked.open...iv/tvurceVysledku	Vaněk, Jan Zelinka, Jan Zajíc, Zbyněk Müller, Luděk
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open.../riv/zahajeniAkce	2014-10-05 (xsd:date)
issn	0302-9743
number of pages	8 (xsd:int)
http://bibframe.org/vocab/doi	10.1007/978-3-319-11581-8_20
http://purl.org/ne...btex#hasPublisher	Springer-Verlag
https://schema.org/isbn	978-3-319-11580-1
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, 58 GB memory in use)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software