The SRI NIST 2010 Speaker Recognition Evaluation System (PREPRINT)

Abstract

The SRI speaker recognition system for the 2010 NIST speaker recognition evaluation (SRE) incorporates multiple subsystemswith a variety of features and modeling techniques. We describe our strategy for this year's evaluation, from the use of speech recognition and speech segmentation to the individual system descriptions as well as the final combination. Our results show that under most conditions, the cepstral systems tend to perform the best, but that other, non-cepstral systems have the most complementarity. The combination of several subsystems with the use of adequate side information gives a 35% improvement on the standard telephone condition. We also show that a constrained cepstral systembased on nasal syllables tends to be more robust to vocal effort variabilities.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 2011
Accession Number
ADA539628

Entities

People

  • Andreas Stolcke
  • Elizabeth Shriberg
  • Luciana Ferrer
  • Martin Graciarena
  • Nicolas Scheffer
  • Sachin Kajarekar

Organizations

  • SRI International

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Adaptive Training
  • Automated Speech Recognition
  • Computer Vision
  • Detection
  • Hidden Markov Models
  • Intelligence Community (United States)
  • Language
  • Markov Models
  • Models
  • Recognition
  • Signal Processing
  • Standards
  • Supervised Machine Learning
  • Syllables
  • Test And Evaluation
  • Training

Readers

  • Operations Research
  • Speech Processing/Speech Recognition.

Technology Areas

  • AI & ML