Pith. sign in

V2S attack: building DNN-based voice conversion from automatic speaker verification

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
abstract

This paper presents a new voice impersonation attack using voice conversion (VC). Enrolling personal voices for automatic speaker verification (ASV) offers natural and flexible biometric authentication systems. Basically, the ASV systems do not include the users' voice data. However, if the ASV system is unexpectedly exposed and hacked by a malicious attacker, there is a risk that the attacker will use VC techniques to reproduce the enrolled user's voices. We name this the ``verification-to-synthesis (V2S) attack'' and propose VC training with the ASV and pre-trained automatic speech recognition (ASR) models and without the targeted speaker's voice data. The VC model reproduces the targeted speaker's individuality by deceiving the ASV model and restores phonetic property of an input voice by matching phonetic posteriorgrams predicted by the ASR model. The experimental evaluation compares converted voices between the proposed method that does not use the targeted speaker's voice data and the standard VC that uses the data. The experimental results demonstrate that the proposed method performs comparably to the existing VC methods that trained using a very small amount of parallel voice data.

fields

cs.CR 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

Evaluating Synthetic Command Attacks on Smart Voice Assistants

cs.CR · 2024-11-13 · conditional · novelty 5.0

Unit-selection diphone synthesis from limited unrelated speech can produce Alexa commands that are recognized with 93.8% accuracy and often receive the highest speaker-similarity confidence, but the headline 30-second success numbers rely on a simulated partial-coverage model with post-hoc donor…

citing papers explorer

Showing 1 of 1 citing paper.

  • Evaluating Synthetic Command Attacks on Smart Voice Assistants cs.CR · 2024-11-13 · conditional · none · ref 27 · internal anchor

    Unit-selection diphone synthesis from limited unrelated speech can produce Alexa commands that are recognized with 93.8% accuracy and often receive the highest speaker-similarity confidence, but the headline 30-second success numbers rely on a simulated partial-coverage model with post-hoc donor…