Interspeech'2005 - Eurospeech
Subphonetic discovery through segmental clustering is a central step in building a corpus-based synthesizer. To help decide what clustering algorithm to use we employed merge-and-split tests on English fricatives. Compared to reference of 2%, Gaussian EM achieved a misclassification rate of 6%, K-means 10%, while predictive CART trees performed poorly.
Bibliographic reference. Kominek, John / Black, Alan W. (2005): "Measuring unsupervised acoustic clustering through phoneme pair merge-and-split tests", In INTERSPEECH-2005, 689-692.