Efficient speaker identification using distributional speaker model clustering

Abstract

For large population speaker identification (SI) systems, likelihood computations between an unknown speaker's test feature vectors and speaker models can be very time-consuming and detrimental to applications where fast SI is required. In this paper, we propose a method whereby speaker models are clustered using a distributional distance measure such as KL divergence during the training stage. During the testing stage, only those clusters which are likely to contain high-likelihood speaker models are searched. The proposed method reduces the speaker model search space which directly results in faster SI. Any loss in identification accuracy can be controlled by trading off speed and accuracy. This paper implements GMM-UBM based SI system with MAP adapted speaker models and the results are presented on TIMIT, NTIMIT and NIST-2002 large population speech corpora.