A method is provided for real-time speaker change detection and speaker tracking in a speech signal. The method is a "coarse-to-refine" process, which consists of two stages: pre-segmentation and refinement. In the pre-segmentation process, the covariance of a feature vector of each segment of speech is built initially. A distance is determined based on the covariance of the current segment and a previous segment; and the distance is used to determine if there is a potential speaker change between these two segments. If there is no speaker change, the model of current identified speaker model is updated by incorporating data of the current segment. Otherwise, if there is a speaker change, a refinement process is utilized to confirm the potential speaker change point.
There is provided an apparatus for providing a Text Independent (TI) speaker recognition mode in a Text Dependent (TD) Hidden Markov Model (HMM) speaker recognition system and/or a Text Constrained (TC) HMM speaker recognition system. The apparatus includes a Gaussian Mixture Model (GMM) generator and a Gaussian weight normalizer. The GMM generator is for creating a GMM by pooling Gaussians from a plurality of HMM states. The Gaussian weight normalizer is for normalizing Gaussian weights with respect to the plurality of HMM states.
