On autoencoders in the i-vector space for speaker recognition

Timur Pekhovsky, Sergey Novoselov, Aleksei Sholohov, Oleg Kudashev


We present the detailed empirical investigation of the speaker verification system based on denoising autoencoder (DAE) in the i-vector space firstly proposed in [1]. This paper includes description of this system and discusses practical issues of the system training. The aim of this investigation is to study the properties of DAE in the i-vector space and analyze different strategies of initialization and training of the the back-end parameters. Also in this paper we propose several improvements to our system to increase the accuracy. Finally, we demonstrate potential of the proposed system in the case of domain mismatch. It achieves considerable gain in performance compared to the baseline system for the unsupervised domain adaptation scenario on the NIST 2010 SRE task.


DOI: 10.21437/Odyssey.2016-31

Cite as

Pekhovsky, T., Novoselov, S., Sholohov, A., Kudashev, O. (2016) On autoencoders in the i-vector space for speaker recognition. Proc. Odyssey 2016, 217-224.

Bibtex
@inproceedings{Pekhovsky+2016,
author={Timur Pekhovsky and Sergey Novoselov and Aleksei Sholohov and Oleg Kudashev},
title={On autoencoders in the i-vector space for speaker recognition},
year=2016,
booktitle={Odyssey 2016},
doi={10.21437/Odyssey.2016-31},
url={http://dx.doi.org/10.21437/Odyssey.2016-31},
pages={217--224}
}