Sheep, Goats, Lambs and Wolves: A Statistical Analysis of Speaker Performance in the NIST 1998 Speaker Recognition Evaluation

Abstract

Performance variability in speech and speaker recognition systems can be attributed to many factors. One major factor, which is often acknowledged but seldom analyzed, is inherent differences in the recognizability of different speakers. In speaker recognition systems such differences are characterized by the use of animal names for different types of speakers, including sheep, goats, lambs and wolves, depending on their behavior with respect to automatic recognition systems. In this paper we propose statistical tests for the existence of these animals and apply these tests to hunt for such animals using results from the 1998 NIST speaker recognition evaluation.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1998
Accession Number
ADA528610

Entities

People

  • Alvin Martin
  • Douglas Reynolds
  • George Doddington
  • Mark Przybocki
  • Walter Liggett

Organizations

  • National Institute of Standards and Technology

Tags

DTIC Thesaurus Topics

  • Abstracts
  • Analysis Of Variance
  • Control Systems
  • Data Science
  • Electrets
  • Entry Control Systems
  • False Alarms
  • Information Science
  • Probability Density Functions
  • Recognition
  • Standards
  • Statistical Analysis
  • Statistical Tests
  • Statistics
  • Test And Evaluation
  • Training
  • Warning Systems

Fields of Study

  • Computer science

Readers

  • Aquatic Ecology
  • Speech Processing/Speech Recognition.
  • Strategic Security Studies

Technology Areas

  • AI & ML