Skip to content
Log in

i-vector

A fixed-length low-dimensional speaker representation extracted by projecting a speaker's UBM statistics into a total variability space. Introduced by Dehak et al. (2011); the dominant speaker recognition paradigm from approximately 2011 to 2018.

Explained in

Related terms

Background population databaseBATVOXC_llr (log-likelihood ratio cost)ENFSI BPMENFSI verbal scaleEqual error rate (EER)NIST SRE (Speaker Recognition Evaluation)PLDA (Probabilistic Linear Discriminant Analysis)x-vector

Your journey to becoming a forensic professional starts here.

Practice with mock tests, learn from structured notes, and get your questions answered by a global forensic community, all in one place.

Continue learningCreate Your Account