In this paper, we study support vector machine based approaches for acoustic modeling of subword units in continuous speech. Classification of subword unit segments is considered as a multi-class pattern recognition problem. In conventional approaches for multi-class pattern recognition using support vector machines, learning involves discrimination of each class against all the other classes. We propose a close-class-set discrimination method suitable for large-classset pattern recognition problems. In the proposed method, learning involves discrimination of each class against a subset of classes confusable with it and included in its close-class-set. We consider different criteria for identification of close-class-sets. We study the effectiveness of the proposed method in reducing the complexity of multi-class pattern recognition systems. We present our studies on recognition of continuous speech segments of 41 mono-phone units in a large corpus of Japanese speech.