Privacy Preserving Speaker Verification using Secure Binary Embeddings

From HLT@INESC-ID

Revision as of 22:32, 2 October 2013 by Rdmr (talk | contribs) (Created page with "__NOTOC__ {{infobox|name=José Portêlo |username=portelo |contact=portelo |phone=+351-213-100-514 |fax=+351-213-145-843 }} == Date == * 15:00, Friday, October 4<sup>th</sup>, ...")
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)
The printable version is no longer supported and may have rendering errors. Please update your browser bookmarks and please use the default browser print function instead.
José Portêlo
José Portêlo

Date

  • 15:00, Friday, October 4th, 2013
  • Room 336

Speaker

Abstract

Conventional remote speaker verification systems rely on the system to have access to the user’s recordings, or features derived from them, and also a model of the user’s voice. In the proposed approach, the system has access to none of them. The features extracted from the user’s recordings are transformed to bit strings in a way that allows the computation of approximate distances, instead of exact ones. The key to the transformation uses a hashing scheme known as Secure Binary Embeddings. An SVM classifier with a modified kernel operates on the hashes. This allows speaker verification to be performed without exposing speaker data. Experiments showed that the secure system yielded similar results as its non-private counterpart. This approach may be extended to other types of biometric authentication.

Retrieved from "https://www.hlt.inesc-id.pt/wiki/index.php?title=Privacy_Preserving_Speaker_Verification_using_Secure_Binary_Embeddings&oldid=7131"