Texto completo
Vista Previa |
PDF (Portable Document Format)
- Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (675kB) | Vista Previa |
Relevance of the glottal pulse and the vocal tract in gender detection
Cita
Muñoz Mulas, Cristina, Martínez Olalla, Rafael 
ORCID: https://orcid.org/0000-0003-2336-9145, Gómez Vilda, Pedro ORCID: https://orcid.org/0000-0003-3283-378X, Álvarez Marquina, Agustín ORCID: https://orcid.org/0000-0002-3387-6709 and Mazaira Fernández, Luis Miguel
(2013).
Relevance of the glottal pulse and the vocal tract in gender detection.
En: "VII Jornadas de Reconocimiento Biométrico de Personas", 12-13 Sept. 2013, Zamora, España. pp. 50-57.
ORCID: https://orcid.org/0000-0003-2336-9145, Gómez Vilda, Pedro ORCID: https://orcid.org/0000-0003-3283-378X, Álvarez Marquina, Agustín ORCID: https://orcid.org/0000-0002-3387-6709 and Mazaira Fernández, Luis Miguel
(2013).
Relevance of the glottal pulse and the vocal tract in gender detection.
En: "VII Jornadas de Reconocimiento Biométrico de Personas", 12-13 Sept. 2013, Zamora, España. pp. 50-57.
Descripción
| Título: | Relevance of the glottal pulse and the vocal tract in gender detection |
|---|---|
| Autor/es: |
|
| Tipo de Documento: | Ponencia en Congreso o Jornada (Otro) |
| Título del Evento: | VII Jornadas de Reconocimiento Biométrico de Personas |
| Fechas del Evento: | 12-13 Sept. 2013 |
| Lugar del Evento: | Zamora, España |
| Fecha: | Septiembre 2013 |
| Materias: | |
| ODS: | |
| Palabras Clave Informales: | Speech processing; Joint-process estimation; Speaker’s biometry; Contextual speech information |
| Escuela: | E.T.S. de Ingenieros Informáticos (UPM) |
| Departamento: | Arquitectura y Tecnología de Sistemas Informáticos |
| Licencias Creative Commons: | Reconocimiento - Sin obra derivada - No comercial |
Resumen
Gender detection is a very important objective to improve efficiency in tasks as speech or speaker recognition, among others. Traditionally gender detection has been focused on fundamental frequency (f0) and cepstral features derived from voiced segments of speech. The methodology presented here consists in obtaining uncorrelated glottal and vocal tract components which are parameterized as mel-frequency coefficients. K-fold and cross-validation using QDA and GMM classifiers showed that better detection rates are reached when glottal source and vocal tract parameters are used in a gender-balanced database of running speech from 340 speakers.
Más información
| ID de Registro: | 32181 |
|---|---|
| Identificador DC: | https://oa.upm.es/32181/ |
| Identificador OAI: | oai:oa.upm.es:32181 |
| Depositado por: | Memoria Investigacion |
| Depositado el: | 14 Oct 2014 10:49 |
| Ultima Modificación: | 19 Feb 2025 12:32 |
Acciones
- Estadísticas
- Exportar cita
- Editar (sólo personal del Archivo)
