A study on GMM-SVM with adaptive relevance factor and its comparison with i-vector and JFA for speaker recognition

Chang Huai You, Haizhou Li, Bin Ma, Kong-Aik Lee

Abstract

Recently, joint factor analysis (JFA) and identity-vector (i-vector) represent the dominant techniques used for speaker recognition due to their superior performance. Developed relatively earlier, the Gaussian mixture model - support vector machine (GMM-SVM) with nuisance attribute projection (NAP) has gradually become less popular. However, when developing the relevance factor in maximum a posteriori (MAP) estimation of GMM to be adapted by application data in place of the conventional fixed value, it is noted that GMM-SVM demonstrates some advantages. In this paper, we conduct a comparative study between GMM-SVM with adaptive relevance factor and JFA/i-vector under the framework of Speaker Recognition Evaluation (SRE) formulated by the National Institute of Standards and Technology (NIST).
BibTeX
@inproceedings{you2013study,
  author = {Chang Huai You and Haizhou Li and Bin Ma and Kong-Aik Lee},
  title = {{A study on GMM-SVM with adaptive relevance factor and its comparison with i-vector and JFA for speaker recognition}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2013},
  doi = {10.1109/icassp.2013.6639158},
}

Loading related content...

Figure