Analysis of Top-K Strategies for Open-Set Speaker Identification Applications

Abstract

Recent performance gains in speaker verification systems suggest it is now viable to employ these systems in open-set speaker identification applications where an automated decision is passed to a human-in-the-loop for final analysis and decision. This paper examines the performance for when a speaker verification system expands into the identification domain. Our results indicate that separate thresholds should be adopted for the verification and the speaker identification phases. Further-more, adopting a top-k approach where the best k matches are passed to the analyst for final matching does not greatly improve system detection performance and has a significant impact on overall human workload.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Mar 01, 2012
Accession Number
AD1108740

Entities

People

  • David Colella
  • Fred Goodman

Organizations

  • MITRE Corporation

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Algorithms
  • Bessel Functions
  • Biometrics
  • Classification
  • Computer Vision
  • Detection
  • Digital Signal Processing
  • Distribution Functions
  • Electrical Engineering
  • Equations
  • Errors
  • Identification
  • Identification Systems
  • Identities
  • New York
  • Order Statistics
  • Probability
  • Random Variables
  • Recognition
  • Sequences
  • Signal Processing
  • Standards
  • Statistics
  • Workload

Fields of Study

  • Computer science

Readers

  • Military History / Militaries and War Studies
  • Sensor Fusion and Tracking Systems.
  • Speech Processing/Speech Recognition.