Abstract
Short-utterance speaker verification presents significant challenges due to the limited information in brief speech segments, which can undermine accuracy and reliability. Recently, zero-shot text-to-speech (ZS-TTS) systems have made considerable progress in preserving speaker identity. In this study, we explore, for the first time, the use of ZS-TTS systems for test-time data augmentation for speaker verification. We evaluate three state-of-the-art pre-trained ZS-TTS systems, NatureSpeech 3, CosyVoice, and MaskGCT, on the VoxCeleb 1 dataset. Our experimental results show that combining real and synthetic speech samples leads to 10%-16% relative equal error rate (EER) reductions across all durations, with particularly notable improvements for short utterances, all without retraining any existing systems. However, our analysis reveals that longer synthetic speech does not yield the same benefits as longer real speech in reducing EERs. These findings highlight the potential and challenges of using ZS-TTS for test-time speaker verification, offering insights for future research.
Abstract (translated)
简短语音的说话人验证由于在短暂语音片段中包含的信息量有限，面临着显著挑战，这可能会削弱其准确性和可靠性。最近，零样本文本到语音（ZS-TTS）系统在保持说话人身份方面取得了重大进展。在这项研究中，我们首次探讨了将ZS-TTS系统用于测试时数据增强以进行说话人验证的潜力。我们在VoxCeleb 1数据集上评估了三个最先进的预训练ZS-TTS系统：NatureSpeech 3、CosyVoice和MaskGCT。实验结果显示，在所有持续时间下，结合真实语音样本与合成语音样本可以实现10%-16%相对等错误率（EER）的降低，尤其是对于简短语句效果更为显著，并且无需重新训练任何现有系统即可达到这一结果。然而，我们的分析还揭示了一个事实：较长的合成语音并未像真实的长语音那样在减少EER方面带来同样的好处。这些发现强调了使用ZS-TTS进行测试时说话人验证的潜力及其面临的挑战，为未来的研究提供了宝贵的见解。
URL
https://arxiv.org/abs/2506.14226
