The present work proposes a method for estimating confidence in speaker identification scores in the time domain. The motivation for this work comes from forensic fingerprinting, where confidence in a captured fingerprint’s capacity to successfully identify its source is determined by the clarity of the print, but, crucially, this clarity may not be consistent across the print. Hicklin et al. [1] propose a standard for assessing confidence in different regions of a fingerprint based on this clarity, allowing for nuanced analysis of fingerprint biometric information. Speech audio poses a similar problem for speaker identification (SID), where there may be variability in the reliability of the scores output by the SID system for different time segments of an audio sample. Here we evaluate acoustic characteristics that can be directly measured from audio to evaluate SID score reliability over time segments of equal length.
Cite as: Bakst, S., Cobo-Kroenke, C., Lawson, A., McLaren, M., Stauffer, A. (2022) Time-Varying Score Reliability Prediction in Speaker Identification. Proc. The Speaker and Language Recognition Workshop (Odyssey 2022), 207-212, doi: 10.21437/Odyssey.2022-29
@inproceedings{bakst22_odyssey,
author={Sarah Bakst and Chris Cobo-Kroenke and Aaron Lawson and Mitchell McLaren and Allen Stauffer},
title={{Time-Varying Score Reliability Prediction in Speaker Identification}},
year=2022,
booktitle={Proc. The Speaker and Language Recognition Workshop (Odyssey 2022)},
pages={207--212},
doi={10.21437/Odyssey.2022-29}
}