ISCA Archive ICSLP 2000
ISCA Archive ICSLP 2000

Optimisation of GMM in speaker recognition

Robert Stapert, John S. Mason, Roland Auckenthaler

Given that the amount of speaker specific training data is always limited, for a given amount of data a speaker model has an optimum number of components. Here, this is investigated with regard to Gaussian mixture models (GMM) with and without world model adaption. Test results show that maximising the number of components in a speaker model can improve speaker recognition results. Comparisons with vector quantisation (VQ) indicate that sensible use of out-of-class data is essential for optimising a recognition system.


Cite as: Stapert, R., Mason, J.S., Auckenthaler, R. (2000) Optimisation of GMM in speaker recognition. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 3, 997-1000

@inproceedings{stapert00_icslp,
  author={Robert Stapert and John S. Mason and Roland Auckenthaler},
  title={{Optimisation of GMM in speaker recognition}},
  year=2000,
  booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
  pages={vol. 3, 997-1000}
}