Joint Cohort Normalization in a Multi-Feature Speaker Verification System

  title={Joint Cohort Normalization in a Multi-Feature Speaker Verification System},
  author={Conrad Sanderson and Kuldip K. Paliwal},
In this paper we propose a new fusion technique, termed Joint Cohort Normalization Fusion, where the information fusion is done prior to the likelihood ratio test in a speaker verification system. The performance of the technique is compared against two popular types of fusion: feature vector concatenation and expert opinion fusion, for fusion of Mel Frequency Cepstral Coefficients (MFCC), MFCC with Cepstral Mean Subtraction (CMS) and Maximum Auto-Correlation Values (MACV) features. In… CONTINUE READING


Publications referenced by this paper.
Showing 1-10 of 12 references

Experimental Evaluation of Features for Robust Speaker Identification

  • D. Reynolds
  • IEEE Trans. Speech and Audio Processing,
  • 1994
1 Excerpt

A Gaussian Mixture Modeling Approach to Text- Independent Speaker Identification

  • D. Reynolds
  • Technical Report 967,
  • 1993
2 Excerpts

Similar Papers

Loading similar papers…