Inter-speaker speech variability assessment using statistical deformable models from 3.0 tesla magnetic resonance images.
Proc Inst Mech Eng H
; 226(3): 185-96, 2012 Mar.
Article
em En
| MEDLINE
| ID: mdl-22558833
ABSTRACT
The morphological and dynamic characterisation of the vocal tract during speech production has been gaining greater attention due to the motivation of the latest improvements in magnetic resonance (MR) imaging; namely, with the use of higher magnetic fields, such as 3.0 Tesla. In this work, the automatic study of the vocal tract from 3.0 Tesla MR images was assessed through the application of statistical deformable models. Therefore, the primary goal focused on the analysis of the shape of the vocal tract during the articulation of European Portuguese sounds, followed by the evaluation of the results concerning the automatic segmentation, i.e. identification of the vocal tract in new MR images. In what concerns speech production, this is the first attempt to automatically characterise and reconstruct the vocal tract shape of 3.0 Tesla MR images by using deformable models; particularly, by using active and appearance shape models. The achieved results clearly evidence the adequacy and advantage of the automatic analysis of the 3.0 Tesla MR images of these deformable models in order to extract the vocal tract shape and assess the involved articulatory movements. These achievements are mostly required, for example, for a better knowledge of speech production, mainly of patients suffering from articulatory disorders, and to build enhanced speech synthesizer models.
Buscar no Google
Coleções:
01-internacional
Base de dados:
MEDLINE
Assunto principal:
Fala
/
Medida da Produção da Fala
/
Prega Vocal
/
Imageamento por Ressonância Magnética
Tipo de estudo:
Diagnostic_studies
/
Prognostic_studies
/
Risk_factors_studies
Limite:
Humans
Idioma:
En
Revista:
Proc Inst Mech Eng H
Assunto da revista:
ENGENHARIA BIOMEDICA
Ano de publicação:
2012
Tipo de documento:
Article
País de afiliação:
Portugal