A smoothing kernel for spatially related features and its application to speaker verification

Luciana Ferrer, Kemal Sönmez, Elizabeth Shriberg

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

Most commonly used kernels are invariant to permutations of the feature vector components. This characteristic may make machine learning methods that use such kernels suboptimal in cases where the feature vector has an underlying structure. In this paper we will consider one such case, where the features are spatially related. We show a way to modify the objective function of the support vector machine (SVM) optimization problem to account for this structure. The new optimization problem can be implemented as a standard SVM using a particular smoothing kernel. Results are shown on a speaker verification task using prosodic features that are transformed using a particular implementation of the Fisher score. The proposed method leads to improvements of as much as 15% in equal error rate (EER).

Original languageEnglish (US)
Title of host publicationInternational Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007
Pages153-156
Number of pages4
StatePublished - Dec 1 2007
Externally publishedYes
Event8th Annual Conference of the International Speech Communication Association, Interspeech 2007 - Antwerp, Belgium
Duration: Aug 27 2007Aug 31 2007

Publication series

NameProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH
Volume1
ISSN (Electronic)1990-9772

Other

Other8th Annual Conference of the International Speech Communication Association, Interspeech 2007
CountryBelgium
CityAntwerp
Period8/27/078/31/07

Keywords

  • Kernels
  • Smoothing
  • Speaker Recognition
  • Speaker Verification
  • Support Vector Machines

ASJC Scopus subject areas

  • Computer Science Applications
  • Software
  • Modeling and Simulation
  • Linguistics and Language
  • Communication

Fingerprint Dive into the research topics of 'A smoothing kernel for spatially related features and its application to speaker verification'. Together they form a unique fingerprint.

  • Cite this

    Ferrer, L., Sönmez, K., & Shriberg, E. (2007). A smoothing kernel for spatially related features and its application to speaker verification. In International Speech Communication Association - 8th Annual Conference of the International Speech Communication Association, Interspeech 2007 (pp. 153-156). (Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH; Vol. 1).