This paper describes a novel method for training a classifier that will perform well after it has been adapted to input speakers. For off-line (batch-mode) adaptation methods which are based on the transformation of classifier parameters, we propose a method for training classifiers. In this method, the classifier is trained while the adaptation to each speaker in the training data is being carried out. The objective function for the training is given based on the recognition performance obtained by the adapted classifier. The utility of the proposed training method is demonstrated by experiments in a five-class Japanese vowel pattern recognition task with speaker adaptation.