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

Simple item page
dc.contributor.authorNouza, Jan
dc.contributor.authorČerva, Petr
dc.contributor.authorKuchařová, Michaela
dc.date.accessioned2016-05-24
dc.date.available2016-05-24
dc.date.issued2013
dc.description.abstractWhen 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
dc.description.sponsorshipCzech Science Foundation [P103/11/P499]; Technology Agency of the Czech Republic [TA01011204]
dc.formattext
dc.identifier.issn1210-2512
dc.identifier.scopus2-s2.0-84885810392
dc.identifier.urihttps://dspace.tul.cz/handle/15240/16393
dc.identifier.urihttps://www.radioeng.cz/fulltexts/2013/13_03_0866_0873.pdf
dc.language.isoen
dc.publisherSpolecnost Pro Radioelektronicke Inzenyrstvi
dc.publisherTechnická Univerzita v Libercics
dc.publisherTechnical university of Liberec, Czech Republicen
dc.relation.ispartofRadioengineeringen
dc.sourcej-scopus
dc.sourcej-wok
dc.subjectSpeech recognitionen
dc.subjectacoustic modelen
dc.subjectcross-lingual adaptationen
dc.subjectSlavic languagesen
dc.titleCost-Efficient Development of Acoustic Models for Speech Recognition of Related Languagesen
dc.typeArticle
local.accessopen
local.citation.epage873
local.citation.spage866
local.facultyFaculty of Mechatronics, Informatics and Interdisciplinary Studies
local.fulltextyes
local.identifier.stagRIV/46747885:24220/13:#0002793
local.identifier.wok324900200026
local.relation.issue3
local.relation.volume22
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
324900200026-o.pdf
Size:
284.22 KB
Format:
Adobe Portable Document Format
Description:
Článek
Download
Collections