Sept. 3, 2000 to Sept. 8, 2000
J. Pelecanos , Queensland University of Technology
S. Myers , Queensland University of Technology
S. Sridharan , Queensland University of Technology
V. Chandran , Queensland University of Technology
Gaussian Mixture Models (GMMs) have become an established means of modeling feature distributions in speaker recognition systems. It is useful for experimentation and practical implementation purposes to develop and test these models in an efficient manner, particularly when computational resources are limited. A method of combining Vector Quantization (VQ) with single multi-dimensional Gaussians is proposed to rapidly generate a robust model approximation to the Gaussian Mixture Model. A fast method of testing these systems is also proposed and implemented. Results on the NIST 1996 Speaker Recognition Database suggest comparable and in some cases, an improved verification performance to the traditional GMM based analysis scheme. In addition, previous research for the task of speaker identification indicated a similar system performance between the VQ Gaussian based technique and GMMs.
J. Pelecanos, S. Myers, S. Sridharan, V. Chandran, "Vector Quantization Based Gaussian Modeling for Speaker Verification", ICPR, 2000, Pattern Recognition, International Conference on, Pattern Recognition, International Conference on 2000, pp. 3298, doi:10.1109/ICPR.2000.903543