Identifying Source Speakers for Voice Conversion based Spoofing Attacks on Speaker Verification Systems

TL;DR

This paper explores identifying the original source speaker from voice-converted speech, demonstrating that training with converted data enhances identification accuracy, especially across different voice conversion models.

Contribution

It introduces a method of training speaker embedding networks with converted speech data labeled by source speaker, improving source speaker identification in voice conversion scenarios.

Findings

Source speaker identification is feasible with converted speech data.

Training with diverse converted utterances improves performance on unseen models.

Adding converted data during training enhances robustness against different voice conversion techniques.

Abstract

An automatic speaker verification system aims to verify the speaker identity of a speech signal. However, a voice conversion system could manipulate a person's speech signal to make it sound like another speaker's voice and deceive the speaker verification system. Most countermeasures for voice conversion-based spoofing attacks are designed to discriminate bona fide speech from spoofed speech for speaker verification systems. In this paper, we investigate the problem of source speaker identification -- inferring the identity of the source speaker given the voice converted speech. To perform source speaker identification, we simply add voice-converted speech data with the label of source speaker identity to the genuine speech dataset during speaker embedding network training. Experimental results show the feasibility of source speaker identification when training and testing with converted speeches from the same voice conversion model(s). In addition, our results demonstrate that having more converted utterances from various voice conversion model for training helps improve the source speaker identification performance on converted utterances from unseen voice conversion models.