TY  - CONF
SN  - 9788469333891
ID  - upm8053
UR  - http://www.ulpgc.es/index.php?pagina=noticia&ver=idetic_30062010
A1  - Gómez Vilda, Pedro
A1  - Álvarez Marquina, Agustin
A1  - Mazaira Fernández, Luis Miguel
A1  - Fernández-Baillo Gallego de la Sacristana, Roberto
A1  - Rodellar Biarge, M. Victoria
A1  - Nieto Lluis, Victor
PB  - Instituto Universitario para el Desarrollo Tecnológico y la Innovación en Comunicaciones
T2  - 1er WTM-IP Workshop de Tecnologías Multibiométricas para la Identificación de Personas
M2  - Universidad de Las Palmas de Gran Canaria
Y1  - 2010///
TI  - Glottal Biometric Features: Are Pathological Voice Studies appliable to Voice Biometry?
AV  - public
CY  - Las Palmas de Gran Canaria, España
N2  - The purpose of the present paper is to introduce a methodology successfully used already in voice pathology detection for its possible adaptation to biometric speaker characterization as well. For such, the behavior of the same GMM classifiers used in the detection of pathology will be exploited. The work will show specific cases derived from running speech typically used in NIST contests against a Universal Background Model built from the population of normophonic subjects in specific vs general evaluation paradigms. Results are contrasted against a set of impostors derived from the same population of normophonic subjects. The relevance of the parameters used in the study will also be discussed
KW  - Speaker Characterization
KW  -  Glottal Source
KW  -  GRBAS
KW  -  Voice Pathology Grading
KW  -  Gaussian Mixture Models
ER  -