Evaluation of Speaker Verification Security and Detection of HMM-Based Synthetic Speech

P.L. De Leon, M. Pucher, J. Yamagishi, I. Hernaez, I. Saratxaga

Research output: Contribution to journalArticlepeer-review

Abstract

In this paper, we evaluate the vulnerability of speaker verification (SV) systems to synthetic speech. The SV systems are based on either the Gaussian mixture model?universal background model (GMM-UBM) or support vector machine (SVM) using GMM supervectors. We use a hidden Markov model (HMM)-based text-to-speech (TTS) synthesizer, which can synthesize speech for a target speaker using small amounts of training data through model adaptation of an average voice or background model. Although the SV systems have a very low equal error rate (EER), when tested with synthetic speech generated from speaker models derived from the Wall Street Journal (WSJ) speech corpus, over 81% of the matched claims are accepted. This result suggests vulnerability in SV systems and thus a need to accurately detect synthetic speech. We propose a new feature based on relative phase shift (RPS), demonstrate reliable detection of synthetic speech, and show how this classifier can be used to improve security of SV systems.
Original languageEnglish
Pages (from-to)2280-2290
Number of pages11
JournalIEEE Transactions on Audio, Speech and Language Processing
Volume20
Issue number8
DOIs
Publication statusPublished - Oct 2012

Keywords

  • Adaptation models
  • Hidden Markov models
  • Speech
  • Support vector machines
  • Synthesizers
  • Training
  • Vectors
  • Security
  • speaker recognition
  • speech synthesis

Fingerprint

Dive into the research topics of 'Evaluation of Speaker Verification Security and Detection of HMM-Based Synthetic Speech'. Together they form a unique fingerprint.

Cite this