About: Cost-Efficient Development of Acoustic Models for Speech Recognition of Related Languages

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

About: Cost-Efficient Development of Acoustic Models for Speech Recognition of Related Languages 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	When adapting an existing speech recognition system to a new language, major development costs are associated with the creation of an appropriate acoustic model (AM). For its training, a certain amount of recorded and annotated speech is required. In this paper, we show that not only the annotation process, but also the process of speech acquisition can be automated to minimize the need of human and expert work. We demonstrate the proposed methodology on Croatian language, for which the target AM has been built via cross-lingual adaptation of a Czech AM in 2 ways: a) using the commercially available GlobalPhone database, and b) by automatic speech data mining from HRT radio archive. The latter approach is cost-free, yet it yields comparable or better results in experiments conducted on 3 Croatian test sets. When adapting an existing speech recognition system to a new language, major development costs are associated with the creation of an appropriate acoustic model (AM). For its training, a certain amount of recorded and annotated speech is required. In this paper, we show that not only the annotation process, but also the process of speech acquisition can be automated to minimize the need of human and expert work. We demonstrate the proposed methodology on Croatian language, for which the target AM has been built via cross-lingual adaptation of a Czech AM in 2 ways: a) using the commercially available GlobalPhone database, and b) by automatic speech data mining from HRT radio archive. The latter approach is cost-free, yet it yields comparable or better results in experiments conducted on 3 Croatian test sets. (en)
Title	Cost-Efficient Development of Acoustic Models for Speech Recognition of Related Languages Cost-Efficient Development of Acoustic Models for Speech Recognition of Related Languages (en)
skos:prefLabel	Cost-Efficient Development of Acoustic Models for Speech Recognition of Related Languages Cost-Efficient Development of Acoustic Models for Speech Recognition of Related Languages (en)
skos:notation	RIV/46747885:24220/13:#0002793!RIV14-GA0-24220___
http://linked.open...avai/riv/aktivita	P
http://linked.open...avai/riv/aktivity	P(GPP103/11/P499), P(TA01011204)
http://linked.open...iv/cisloPeriodika	3
http://linked.open...vai/riv/dodaniDat	2014
http://linked.open...aciTvurceVysledku	Červa, Petr Nouza, Jan Kuchařová, Michaela
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	Technická univerzita v Liberci / Fakulta mechatroniky, informatiky a mezioborových studií
http://linked.open...dnocenehoVysledku	67190
http://linked.open...ai/riv/idVysledku	RIV/46747885:24220/13:#0002793
http://linked.open...riv/jazykVysledku	eng - angličtina
http://linked.open.../riv/klicovaSlova	Speech recognition; acoustic model; cross-lingual adaptation; Slavic languages (en)
http://linked.open.../riv/klicoveSlovo	Speech recognition cross-lingual adaptation acoustic model Slavic languages
http://linked.open...odStatuVydavatele	CZ - Česká republika
http://linked.open...ontrolniKodProRIV	[3C881643F9E5]
http://linked.open...i/riv/nazevZdroje	Radioengineering
http://linked.open...in/vavai/riv/obor	JC
http://linked.open...ichTvurcuVysledku	3 (xsd:int)
http://linked.open...cetTvurcuVysledku	3 (xsd:int)
http://linked.open...vavai/riv/projekt	Living Archives Speaker Adaptation Methods in Speech Recognition Systems
http://linked.open...UplatneniVysledku	2013
http://linked.open...v/svazekPeriodika	22
http://linked.open...iv/tvurceVysledku	Nouza, Jan Červa, Petr Kuchařová, Michaela
http://linked.open...ain/vavai/riv/wos	000324900200026
issn	1210-2512
number of pages	8 (xsd:int)
http://localhost/t...ganizacniJednotka	24220

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