Evaluations of Automatic Speaker Classification Systems

Authors:
Alvin F. Martin
Affiliations:
National Institute of Standards and Technology, 100 Bureau Drive Stop 8940, Gaithersburg, MD 20899-8940,
Venue:
Speaker Classification I
Year:
2007

Citing 5
Cited 3

The NIST speaker recognition evaluation - overview methodology, systems, results, perspective

Speech Communication - Speaker recognition and its commercial and forensic applications
An Introduction to Evaluating Biometric Systems

Computer
An Introduction to Evaluating Biometric Systems

Computer
The rich transcription 2005 spring meeting recognition evaluation

MLMI'05 Proceedings of the Second international conference on Machine Learning for Multimodal Interaction
The rich transcription 2006 spring meeting recognition evaluation

MLMI'06 Proceedings of the Third international conference on Machine Learning for Multimodal Interaction

Higher-Level Features in Speaker Recognition

Speaker Classification I
An Introduction to Application-Independent Evaluation of Speaker Recognition Systems

Speaker Classification I
Durations of Context-Dependent Phonemes: A New Feature in Speaker Verification

Speaker Classification II

Quantified Score

Hi-index	0.00

Visualization

Abstract

The annual NIST Speaker Recognition Evaluations (SREs) from 1996 to 2006 have been internationally recognized as the leading source or performance evaluation of research systems in the speaker classification field. We discuss how these evaluations have developed and been conducted and the performance measures used. We consider the key factors that have been studied for their effect on performance, including training and test durations, channel variability, and speaker variability. We examine the extent to which progress has been observed in state-of-the-art performance. We also consider how the technology has changed over the past decade, other evaluations that have been conducted or planned, and where the field may be headed in the future.