Introducing non-linear analysis into sustained speech characterization to improve sleep apnea detection

Blanco Murillo, José Luis y Hernández Gómez, Luis Alfonso (2011). Introducing non-linear analysis into sustained speech characterization to improve sleep apnea detection. En: "NOLISP'11 Proceedings of the 5th international conference on Advances in nonlinear speech processing", 07/11/2011 - 08/11/2011, Las Palmas de Gran Canaria, España. ISBN 978-3-642-25019-4. pp. 1-9.

Descripción

Título: Introducing non-linear analysis into sustained speech characterization to improve sleep apnea detection
Autor/es:
  • Blanco Murillo, José Luis
  • Hernández Gómez, Luis Alfonso
Tipo de Documento: Ponencia en Congreso o Jornada (Artículo)
Título del Evento: NOLISP'11 Proceedings of the 5th international conference on Advances in nonlinear speech processing
Fechas del Evento: 07/11/2011 - 08/11/2011
Lugar del Evento: Las Palmas de Gran Canaria, España
Título del Libro: Proceedings of NOLISP'11 Proceedings of the 5th international conference on Advances in nonlinear speech processing
Fecha: 2011
ISBN: 978-3-642-25019-4
Materias:
Escuela: E.T.S.I. Telecomunicación (UPM)
Departamento: Señales, Sistemas y Radiocomunicaciones
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (395kB) | Vista Previa

Resumen

We present a novel approach for detecting severe obstructive sleep apnea (OSA) cases by introducing non-linear analysis into sustained speech characterization. The proposed scheme was designed for providing additional information into our baseline system, built on top of state-of-the-art cepstral domain modeling techniques, aiming to improve accuracy rates. This new information is lightly correlated with our previous MFCC modeling of sustained speech and uncorrelated with the information in our continuous speech modeling scheme. Tests have been performed to evaluate the improvement for our detection task, based on sustained speech as well as combined with a continuous speech classifier, resulting in a 10% relative reduction in classification for the first and a 33% relative reduction for the fused scheme. Results encourage us to consider the existence of non-linear effects on OSA patients' voices, and to think about tools which could be used to improve short-time analysis.

Más información

ID de Registro: 12939
Identificador DC: http://oa.upm.es/12939/
Identificador OAI: oai:oa.upm.es:12939
URL Oficial: http://www.springer.com/computer/image+processing/book/978-3-642-25019-4
Depositado por: Memoria Investigacion
Depositado el: 12 Dic 2012 16:12
Ultima Modificación: 21 Abr 2016 12:15
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • e-ciencia
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM