Automatic intelligibility classification of sentence-level pathological speech

•We propose novel sentence-level features to capture atypical variation.•Our sentence-level features are effective for intelligibility classification.•We propose a post-classification posterior smoothing scheme.•Our smoothing scheme improves classification accuracy of our systems.•We test feature-le...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Computer speech & language 2015-01, Vol.29 (1), p.132-144
Hauptverfasser:	Kim, Jangwon, Kumar, Naveen, Tsiartas, Andreas, Li, Ming, Narayanan, Shrikanth S.
Format:	Artikel
Sprache:	eng
Schlagworte:	Automatic intelligibility assessment Automation Classification Dysarthric speech Head and neck cancer Intelligibility Linguistics Pathological speech Smoothing Speech Voice
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!