End-to-end DNN based text-independent speaker recognition for long and short utterances

Recently several end-to-end speaker verification systems based on deep neural networks (DNNs) have been proposed. These systems have been proven to be competitive for text-dependent tasks as well as for text-independent tasks with short utterances. However, for text-independent tasks with longer utt...

Full description

Saved in:
Bibliographic Details
Published in:Computer speech & language 2020-01, Vol.59, p.22-35
Main Authors: Rohdin, Johan, Silnova, Anna, Diez, Mireia, Plchot, Oldřich, Matějka, Pavel, Burget, Lukáš, Glembek, Ondřej
Format: Article
Language:English
Subjects:
DNN
End-to-end
i-vector
PLDA
Speaker verification
Text-independent
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently several end-to-end speaker verification systems based on deep neural networks (DNNs) have been proposed. These systems have been proven to be competitive for text-dependent tasks as well as for text-independent tasks with short utterances. However, for text-independent tasks with longer utterances, end-to-end systems are still outperformed by standard i-vector + PLDA systems. In this work, we present an end-to-end speaker verification system that is initialized to mimic an i-vector + PLDA baseline. The system is then further trained in an end-to-end manner but regularized so that it does not deviate too far from the initial system. In this way we mitigate overfitting which normally limits the performance of end-to-end systems. The proposed system outperforms the i-vector + PLDA baseline on both long and short duration utterances.
ISSN:0885-2308
1095-8363
DOI:10.1016/j.csl.2019.06.002