privacy-preserving-ivector.pdf (572.98 kB)
Download file

Privacy-preserving iVector-based speaker verification

Download (572.98 kB)
journal contribution
posted on 04.12.2018, 12:05 by Yogachandran RahulamathavanYogachandran Rahulamathavan, R. Sutharsini Kunaraj, Ray Indranil Ghosh, Rongxing Lu, Muttukrishnan Rajarajan
This work introduces an efficient algorithm to develop a privacy-preserving (PP) voice verification based on iVector and linear discriminant analysis techniques. This research considers a scenario in which users enrol their voice biometric to access different services (i.e., banking). Once enrolment is completed, users can verify themselves using their voice-print instead of alphanumeric passwords. Since a voice-print is unique for everyone, storing it with a third-party server raises several privacy concerns. To address this challenge, this work proposes a novel technique based on randomisation to carry out voice authentication, which allows the user to enrol and verify their voice in the randomised domain. To achieve this, the iVector based voice verification technique has been redesigned to work on the randomised domain. The proposed algorithm is validated using a well known speech dataset. The proposed algorithm neither compromises the authentication accuracy nor adds additional complexity due to the randomisation operations.

Funding

The work was supported by the EU Horizon2020 programme under EU Grant H2020-EU.3.7 (Project ID: 653586), NSERC Discovery Grants (04009) and LMCRF-S-2018-03.

History

School

  • Loughborough University London

Published in

IEEE/ACM Transactions on Audio, Speech, and Language Processing

Volume

27

Issue

3

Pages

496 - 506

Citation

RATHULAMATHAVAN, Y. ... et al., 2018. Privacy-preserving iVector-based speaker verification. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 27(3), pp. 496 - 506.

Publisher

© Institute of Electrical and Electronics Engineers

Version

AM (Accepted Manuscript)

Acceptance date

04/11/2018

Publication date

2018-11-21

Notes

Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

ISSN

2329-9290

eISSN

2329-9304

Language

en

Usage metrics

Read the paper on the publisher website

Categories

Exports