A cross-lingual adaptation approach for rapid development of speech recognizers for learning disabled users

dc.contributor.authorBoháč, Marek
dc.contributor.authorKuchařová, Michaela
dc.contributor.authorCallejas, Zoraida
dc.contributor.authorNouza, Jan
dc.contributor.authorČerva, Petr
dc.date.accessioned2016-05-24
dc.date.available2016-05-24
dc.date.issued2014
dc.description.abstractBuilding a voice-operated system for learning disabled users is a difficult task that requires a considerable amount of time and effort. Due to the wide spectrum of disabilities and their different related phonopathies, most approaches available are targeted to a specific pathology. This may improve their accuracy for some users, but makes them unsuitable for others. In this paper, we present a cross-lingual approach to adapt a general-purpose modular speech recognizer for learning disabled people. The main advantage of this approach is that it allows rapid and cost-effective development by taking the already built speech recognition engine and its modules, and utilizing existing resources for standard speech in different languages for the recognition of the usersatypical voices. Although the recognizers built with the proposed technique obtain lower accuracy rates than those trained for specific pathologies, they can be used by a wide population and developed more rapidly, which makes it possible to design various types of speech-based applications accessible to learning disabled users.en
dc.description.sponsorshipproject 'Favoreciendo la vida autonoma de discapacitados intelectuales con problemas de comunicacion oral mediante interfaces personalizados de reconocimiento automatico del habla'; Technical University of Liberec
dc.formattext
dc.identifier.doi10.1186/s13636-014-0039-0
dc.identifier.issn1687-4722
dc.identifier.scopus2-s2.0-84919914195
dc.identifier.urihttps://asmp-eurasipjournals.springeropen.com/articles/10.1186/s13636-014-0039-0
dc.language.isoen
dc.publisherSpringer International Publishing Ag
dc.publisherTechnická Univerzita v Libercics
dc.publisherTechnical university of Liberec, Czech Republicen
dc.relation.ispartofEurasip Journal On Audio Speech And Music Processingen
dc.sourcej-scopus
dc.sourcej-wok
dc.subjectAutomatic speech recognitionen
dc.subjectCross-lingual adaptationen
dc.subjectAssistive technologyen
dc.subjectSpeech technologyen
dc.subjectAtypical voicesen
dc.subjectLearning disableden
dc.subjectIntellectual disabilityen
dc.subjectDysarthriaen
dc.titleA cross-lingual adaptation approach for rapid development of speech recognizers for learning disabled usersen
dc.typeArticle
local.accessopen
local.departmentInstitute of Information Technology and Electronics
local.facultyFaculty of Mechatronics, Informatics and Interdisciplinary Studies
local.fulltextno
local.fulltextyes
local.identifier.wok347392900001
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
2-s2.0-84919914195-o.pdf
Size:
589.57 KB
Format:
Adobe Portable Document Format
Description:
Článek
Collections