Memorias de investigación
Communications at congresses:
Analyzing training dependencies and posterior fusion in discriminant classification of apnoea patients based on sustained and connected speech
Year:2011

Research Areas
  • Processing and signal analysis

Information
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.
International
Si
Congress
12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011
960
Place
Reviewers
Si
ISBN/ISSN
1990-9772
Start Date
27/08/2011
End Date
31/08/2011
From page
3033
To page
3036
12th Annual Conference of the International Speech Communication Association, INTERSPEECH 2011
Participants

Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: Grupo de Aplicaciones del Procesado de Señal (GAPS)
  • Departamento: Señales, Sistemas y Radiocomunicaciones