Analyzing training dependencies and posterior fusion in discriminant classification of apnoea patients based on sustained and connected speech

Blanco Murillo, José Luis and Fernández Pozo, Rubén and Torre Toledano, Doroteo and Caminero Gil, Francisco Javier and Lopez Gonzalo, Eduardo (2011). Analyzing training dependencies and posterior fusion in discriminant classification of apnoea patients based on sustained and connected speech. In: "12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011", 27/08/2011 - 31/08/2011, Florence Italy. pp. 3033-3036.

Description

Title: Analyzing training dependencies and posterior fusion in discriminant classification of apnoea patients based on sustained and connected speech
Author/s:
  • Blanco Murillo, José Luis
  • Fernández Pozo, Rubén
  • Torre Toledano, Doroteo
  • Caminero Gil, Francisco Javier
  • Lopez Gonzalo, Eduardo
Item Type: Presentation at Congress or Conference (Article)
Event Title: 12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011
Event Dates: 27/08/2011 - 31/08/2011
Event Location: Florence Italy
Title of Book: 12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011
Date: 2011
Subjects:
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Señales, Sistemas y Radiocomunicaciones
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (112kB) | Preview

Abstract

We present a novel approach using both sustained vowels and connected speech, to detect obstructive sleep apnea (OSA) cases within a homogeneous group of speakers. The proposed scheme is based on state-of-the-art GMM-based classifiers, and acknowledges specifically the way in which acoustic models are trained on standard databases, as well as the complexity of the resulting models and their adaptation to specific data. Our experimental database contains a suitable number of utterances and sustained speech from healthy (i.e control) and OSA Spanish speakers. Finally, a 25.1% relative reduction in classification error is achieved when fusing continuous and sustained speech classifiers. Index Terms: obstructive sleep apnea (OSA), gaussian mixture models (GMMs), background model (BM), classifier fusion.

More information

Item ID: 12940
DC Identifier: http://oa.upm.es/12940/
OAI Identifier: oai:oa.upm.es:12940
Deposited by: Memoria Investigacion
Deposited on: 26 Feb 2013 08:58
Last Modified: 21 Apr 2016 12:15
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM