A fast Speaker Identification method using nearest neighbor distance

By increasing the number of registered speakers in Speaker Identification (SI) systems, computation time for identifying an unknown speaker is significantly increased. This problem arises from the simple design of conventional methods. Due to this limitation, we cannot use conventional SI methods in real time applications. In this paper, we propose a two-step method to overcome this limitation. We use different identification methods for each step. In the first step we reduce the search space using Nearest Neighbor method. In the second step we identify the target speaker using the conventional GMM-based SI method. The experimental results show 3.4× speed-ups without any accuracy loss using the proposed method. It is also shown that if the number of selected speakers in first step is furthermore reduced, the identification speed will increase, at the cost of a slight decrease of accuracy. So, there is a trade-off between accuracy and speed-up that can be controlled by a threshold.