Chetupalli, S.R.Gopalakrishnan, A.Sreenivas, T.V.2026-02-062016European Signal Processing Conference, 2016, Vol.2016-November, , p. 135-13922195491https://doi.org/10.1109/EUSIPCO.2016.7760225https://idr.nitk.ac.in/handle/123456789/32011We explore, experimentally, feature selection and optimization of stochastic model parameters for the problem of speaker spotting. Based on an initially identified segment of speech of a speaker, an iterative model refinement method is developed along with a latent variable mixture model so that segments of the same speaker are identified in a long speech record. It is found that a GMM with moderate number of mixtures is better suited for the task than a large number mixture model as used in speaker identification. Similarly, a PCA based low-dimensional projection of MFCC based feature vector provides better performance. We show that about 6 seconds of initially identified speaker data is sufficient to achieve > 90% performance of speaker segment identification. © 2016 IEEE.Gaussian mixture model (GMM)Mel-frequency cepstral coefficients (MFCCs)Speaker diarizationSpeaker spottingSpeaker verification