Methodological issues in the development of automatic systems for voice pathology detection

This paper describes some methodological concerns to be considered when designing systems for automatic detection of voice pathology, in order to enable comparisons to be made with previous or future experiments. The proposed methodology is built around the Massachusetts Eye & Far Infirmary, (MEEI) Voice Disorders Database, which to the present date is the only commercially available one. Discussion about key points on this database is included. Any experiment should have a cross-validation strategy, and results should supply, along with the final confusion matrix, confidence intervals for all measures. Detector performance curves such as detector error trade off (DET) and receiver operating characteristic (ROC) plots are also considered. An example of the methodology is provided, with an experiment based on short-term parameters and multi-layer perceptrons. (C) 2006 Elsevier Ltd. All rights reserved.