8th Annual Conference of the International Speech Communication Association

Antwerp, Belgium
August 27-31, 2007

Articulatory Feature Classifiers Trained on 2000 hours of Telephone Speech

Joe Frankel (1), Mathew Magimai-Doss (2), Simon King (1), Karen Livescu (3), Özgür Çetin (2)

(1) University of Edinburgh, UK
(3) MIT, USA

This paper is intended to advertise the public availability of the articulatory feature (AF) classification multi-layer perceptrons (MLPs) which were used in the Johns Hopkins 2006 summer workshop. We describe the design choices, data preparation, AF label generation, and the training of MLPs for feature classification on close to 2000 hours of telephone speech. In addition, we present some analysis of the MLPs in terms of classification accuracy and confusions along with a brief summary of the results obtained during the workshop using the MLPs. We invite interested parties to make use of these MLPs.

Full Paper

Bibliographic reference.  Frankel, Joe / Magimai-Doss, Mathew / King, Simon / Livescu, Karen / Çetin, Özgür (2007): "Articulatory feature classifiers trained on 2000 hours of telephone speech", In INTERSPEECH-2007, 2485-2488.