Advanced Subspace Techniques for Modeling Channel and Session Variability in a Speaker Recognition System

Abstract

The robustness of any speaker recognition system is dependent on its capability for managing the variability in the recording environment. A better ability to quantify that variation may lead to the development of improved methods for reducing the non-speaker influences on performance. In this study, subspace decomposition in combination with three pattern classification techniques was investigated to assess its appropriateness for performing speaker recognition on the MultiRoom8 corpus, a data set with several room and microphone conditions. A partial least squares decomposition of the GMM supervector in combination with a nearest neighbor classifier was consistently a top-performer on the 100 experimental setups consider in this study, which may suggest an approach for mitigating the effects of room and microphone variability in a speaker recognition system through projections to a lower-dimensional feature space.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2012
Accession Number
ADA557785

Entities

People

  • Jeremiah Remus

Organizations

  • Clarkson University

Tags

Communities of Interest

  • Biomedical
  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Air Force
  • Air Force Research Laboratories
  • Algorithms
  • Classification
  • Computational Complexity
  • Computational Science
  • Data Science
  • Data Sets
  • Decomposition
  • Dimensionality Reduction
  • Factor Analysis
  • Information Science
  • Machine Learning
  • Pattern Recognition
  • Recognition
  • Supervised Machine Learning
  • Test Sets

Readers

  • Computer Networking
  • Linear Algebra
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML
  • Space