Joint frame and Gaussian selection for text independent speaker verification

Rahim Saeidi, Tomi Kinnunen, Hamid Reza Sadegh Mohammadi, Robert Rodman, Pasi Franti
2010 2010 IEEE International Conference on Acoustics, Speech and Signal Processing  
Gaussian selection is a technique applied in the GMM-UBM framework to accelerate score calculation. We have recently introduced a novel Gaussian selection method known as sorted GMM (SGMM). SGMM uses scalar-indexing of the universal background model mean vectors to achieve fast search of the topscoring Gaussians. In the present work we extend this method by using 2-dimensional indexing, which leads to simultaneous frame and Gaussian selection. Our results on the NIST 2002 speaker recognition
more » ... aker recognition evaluation corpus indicate that both the 1-and 2dimensional SGMMs outperform frame decimation and temporal tracking of top-scoring Gaussians by a wide margin (in terms of Gaussian computations relative to GMM-UBM as baseline).
doi:10.1109/icassp.2010.5495576 dblp:conf/icassp/SaeidiKMRF10 fatcat:xf2iukoib5aydppvmajs7ipz24