About: Knowledge-Based and Automated Clustering in MLLR Adaptation of Acoustic Models for LVCSR

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

About: Knowledge-Based and Automated Clustering in MLLR Adaptation of Acoustic Models for LVCSR 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
Description	This paper describes the analysis of the performance of MLLR-based speaker adaptation in a large vocabulary continuous speech recognition system. Two different approaches of clustering in MLLR-adaptation with more regression classes, knowledge-based clustering and automatic clustering were analysed. The contribution of mentioned acoustic model adaptation using these two clustering approaches were compared based on the word error rate ratio (WERR) of target LVCSR. Realized study proved that the knowledge-based clustering may bring improvement comparable to the tree-based clustering, when only a few transformation classes are manually defined. This paper describes the analysis of the performance of MLLR-based speaker adaptation in a large vocabulary continuous speech recognition system. Two different approaches of clustering in MLLR-adaptation with more regression classes, knowledge-based clustering and automatic clustering were analysed. The contribution of mentioned acoustic model adaptation using these two clustering approaches were compared based on the word error rate ratio (WERR) of target LVCSR. Realized study proved that the knowledge-based clustering may bring improvement comparable to the tree-based clustering, when only a few transformation classes are manually defined. (en)
Title	Knowledge-Based and Automated Clustering in MLLR Adaptation of Acoustic Models for LVCSR Knowledge-Based and Automated Clustering in MLLR Adaptation of Acoustic Models for LVCSR (en)
skos:prefLabel	Knowledge-Based and Automated Clustering in MLLR Adaptation of Acoustic Models for LVCSR Knowledge-Based and Automated Clustering in MLLR Adaptation of Acoustic Models for LVCSR (en)
skos:notation	RIV/68407700:21230/12:00196164!RIV13-MSM-21230___
http://linked.open...avai/predkladatel	Fakulta elektrotechnická
http://linked.open...avai/riv/aktivita	S
http://linked.open...avai/riv/aktivity	S
http://linked.open...vai/riv/dodaniDat	2013
http://linked.open...aciTvurceVysledku	Pollák, Petr Borský, Michal
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	České vysoké učení technické v Praze / Fakulta elektrotechnická
http://linked.open...dnocenehoVysledku	144862
http://linked.open...ai/riv/idVysledku	RIV/68407700:21230/12:00196164
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	MLLR; LVCSR; adaptation; regression classes; acoustic modelling (en)
http://linked.open.../riv/klicoveSlovo	LVCSR adaptation acoustic modelling regression classes MLLR
http://linked.open...ontrolniKodProRIV	[8E515735AB2B]
http://linked.open...v/mistoKonaniAkce	Plzeň
http://linked.open...i/riv/mistoVydani	Pilsen
http://linked.open...i/riv/nazevZdroje	2012 International Conference on Applied Electronics
http://linked.open...in/vavai/riv/obor	JA
http://linked.open...ichTvurcuVysledku	2 (xsd:int)
http://linked.open...cetTvurcuVysledku	2 (xsd:int)
http://linked.open...UplatneniVysledku	2012
http://linked.open...iv/tvurceVysledku	Pollák, Petr Borský, Michal
http://linked.open...vavai/riv/typAkce	EUR - Evropská
http://linked.open...ain/vavai/riv/wos	000305136600002
http://linked.open.../riv/zahajeniAkce	2012-09-06 (xsd:date)
issn	1803-7232
number of pages	4 (xsd:int)
http://purl.org/ne...btex#hasPublisher	Západočeská univerzita v Plzni
https://schema.org/isbn	978-80-261-0038-6
http://localhost/t...ganizacniJednotka	21230
is http://linked.open...avai/riv/vysledek of	Knowledge-Based and Automated Clustering in MLLR Adaptation of Acoustic Models for LVCSR

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