Ensemble Learning and Optimizing KNN Method for Speaker Recognition

Ensemble with K Nearest Neighbor (KNN) learner is a novel approach to speaker recognition. It has many advantages over other conversational methods such as simplicity and good generalization ability. At the same time, the generalization ability of an ensemble could be significantly better than that of a single learner. In this paper, we intend to improve the performance of the speaker recognition system by introducing a novel method combining optimizing annular region-weighted distance k nearest neighbor with BagWithProb ensemble learning schemes. Experiments studied in this paper indicate that the proposed method can effectively improve the accuracy of speaker identification system.