Nonparametric feature normalization for SVM-based speaker verification

Andreas Stolcke, Sachin S. Kajarekar, Luciana FerrerICASSP 2008 · OpenReview

Abstract

We investigate several feature normalization and scaling approaches for use in speaker verification based on support vector machines. We are particularly interested in methods that are "knowledge-free" and work for a variety of features, leading us to investigate MLLR transforms, phone N-grams, prosodic sequences, and word N-gram features. Normalization methods studied include mean/variance normalization, TFLLR and TFLOG scaling, and a simple nonparametric approach: rank-normalization. We find that rank-normalization is uniformly competitive with other methods, and improves upon them in many cases.
BibTeX
@inproceedings{stolcke2008nonparametric,
  author = {Andreas Stolcke and Sachin S. Kajarekar and Luciana Ferrer},
  title = {{Nonparametric feature normalization for SVM-based speaker verification}},
  booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
  year = {2008},
  url = {https://openreview.net/forum?id=QATz4tTK0Q},
}

Loading related content...

Figure