Diffusion maps for PLDA-based speaker verification

During the last few years, i-vectors have become an important component in most state-of-the-art speaker recognition systems. I-vector extraction is based on an assumption that GMM supervectors reside on a low dimensional space, which is modeled using Factor Analysis. In this paper we replace the ab...

Full description

Saved in:
Bibliographic Details
Published in2013 IEEE International Conference on Acoustics, Speech and Signal Processing pp. 7639 - 7643
Main Authors Barkan, Oren, Aronowitz, Hagai
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.05.2013
Subjects
Diffusion Maps
Diffusion processes
Feature extraction
Harmonic analysis
ivectors
Manifolds
NIST
Non-linear dimensionality reduction
Pattern recognition
Speaker recognition
Speaker verification
Vectors
Online AccessGet full text

Cover

More Information
Summary:During the last few years, i-vectors have become an important component in most state-of-the-art speaker recognition systems. I-vector extraction is based on an assumption that GMM supervectors reside on a low dimensional space, which is modeled using Factor Analysis. In this paper we replace the above assumption with an assumption that the GMM supervectors reside on a low dimensional manifold and propose to use Diffusion Maps to learn that manifold. The learnt manifold implies a mapping of spoken sessions into a modified i-vector space which we call d-vector space. D-vectors can further be processed using standard techniques such as LDA, WCCN, cosine distance scoring or Probabilistic Linear Discriminant Analysis (PLDA). We demonstrate the usefulness of our approach on the telephone core conditions of NIST 2010, and obtain significant error reduction.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.2013.6639149