About: Region Dependent Linear Transforms in Multilingual Speech Recognition

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

About: Region Dependent Linear Transforms in Multilingual Speech Recognition 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	In today's speech recognition systems, linear or nonlinear transformations are usually applied to post-process speech features forming input to HMM based acoustic models. In this work, we experiment with three popular transforms: HLDA,MPE-HLDA and Region Dependent Linear Transforms (RDLT), which are trained jointly with the acoustic model to extract maximum of the discriminative information from the raw features and to represent it in a form suitable for the following GMM-HMM based acoustic model. We focus on multi-lingual environments, where limited resources are available for training recognizers of many languages. Using data from GlobalPhone database, we show that, under such restrictive conditions, the feature transformations can be advantageously shared across languages and robustly trained using data from several languages. In today's speech recognition systems, linear or nonlinear transformations are usually applied to post-process speech features forming input to HMM based acoustic models. In this work, we experiment with three popular transforms: HLDA,MPE-HLDA and Region Dependent Linear Transforms (RDLT), which are trained jointly with the acoustic model to extract maximum of the discriminative information from the raw features and to represent it in a form suitable for the following GMM-HMM based acoustic model. We focus on multi-lingual environments, where limited resources are available for training recognizers of many languages. Using data from GlobalPhone database, we show that, under such restrictive conditions, the feature transformations can be advantageously shared across languages and robustly trained using data from several languages. (en)
Title	Region Dependent Linear Transforms in Multilingual Speech Recognition Region Dependent Linear Transforms in Multilingual Speech Recognition (en)
skos:prefLabel	Region Dependent Linear Transforms in Multilingual Speech Recognition Region Dependent Linear Transforms in Multilingual Speech Recognition (en)
skos:notation	RIV/00216305:26230/12:PU98188!RIV14-GA0-26230___
http://linked.open...avai/predkladatel	Fakulta informačních technologií
http://linked.open...avai/riv/aktivita	P Z
http://linked.open...avai/riv/aktivity	P(FR-TI1/034), P(GPP202/12/P604), P(TA01011328), Z(MSM0021630528)
http://linked.open...vai/riv/dodaniDat	2014
http://linked.open...aciTvurceVysledku	Burget, Lukáš Černocký, Jan Karafiát, Martin Janda, Miloš
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	Vysoké učení technické v Brně / Fakulta informačních technologií
http://linked.open...dnocenehoVysledku	164601
http://linked.open...ai/riv/idVysledku	RIV/00216305:26230/12:PU98188
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	HLDA, Region Dependent Transforms, Minimum Phone Error, fMPE, multilingual speech recognition (en)
http://linked.open.../riv/klicoveSlovo	HLDA Minimum Phone Error Region Dependent Transforms fMPE multilingual speech recognition
http://linked.open...ontrolniKodProRIV	[1320E1C2F336]
http://linked.open...v/mistoKonaniAkce	Kyoto
http://linked.open...i/riv/mistoVydani	Kyoto
http://linked.open...i/riv/nazevZdroje	Proc. International Conference on Acoustics, Speech, and Signal Processing 2012
http://linked.open...in/vavai/riv/obor	JC
http://linked.open...ichTvurcuVysledku	4 (xsd:int)
http://linked.open...cetTvurcuVysledku	4 (xsd:int)
http://linked.open...vavai/riv/projekt	Multilingual recognition and search in speech for electronic dicionaries Technologies of speech processing for efficient human-machine communication Speech recognition for low-resource languages
http://linked.open...UplatneniVysledku	2012
http://linked.open...iv/tvurceVysledku	Burget, Lukáš Karafiát, Martin Černocký, Jan Janda, Miloš
http://linked.open...vavai/riv/typAkce	WRD - Světová
http://linked.open...ain/vavai/riv/wos	000312381404239
http://linked.open.../riv/zahajeniAkce	2012-03-25 (xsd:date)
http://linked.open...n/vavai/riv/zamer	Výzkum informačních technologií z hlediska bezpečnosti
number of pages	4 (xsd:int)
http://bibframe.org/vocab/doi	10.1109/ICASSP.2012.6289014
http://purl.org/ne...btex#hasPublisher	IEEE Signal Processing Society
https://schema.org/isbn	978-1-4673-0044-5
http://localhost/t...ganizacniJednotka	26230

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