Supervector Bayesian speaker comparison

@article{Borgstrom2013SupervectorBS,
  title={Supervector Bayesian speaker comparison},
  author={Bengt J. Borgstrom and Alan McCree},
  journal={2013 IEEE International Conference on Acoustics, Speech and Signal Processing},
  year={2013},
  pages={7693-7697}
}
In this paper we propose fully Bayesian speaker comparison of supervectors, which we refer to as SV-BSC, as a method for estimating whether a test cut was generated by the same speaker as an enrollment set. We derive the SV-BSC log-likelihood ratio of same-speaker to different-speaker hypotheses, and present solutions for model training and Bayesian scoring. We then show that if speaker and channel variability are assumed to inhabit a total variability subspace, SV-BSC scoring reduces to a form… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 10 CITATIONS

Similar Papers

Loading similar papers…