A standard recipe for spoken language recognition is to apply a Gaussian back-end to i-vectors. This ignores the uncertainty in the i-vector extraction, which could be important especially for short utterances. A recent paper by Cumani, Plchot and Fer proposes a solution to propagate that uncertainty into the backend. We propose an alternative method of propagating the uncertainty.
Cite
@article{arxiv.1710.00085,
title = {Language-depedent I-Vectors for LRE15},
author = {Niko Brümmer and Albert Swart},
journal= {arXiv preprint arXiv:1710.00085},
year = {2017}
}