PhonemeDF:用于音频深度伪造检测和自然度评估的合成语音数据集
PhonemeDF: A Synthetic Speech Dataset for Audio Deepfake Detection and Naturalness Evaluation
AI总结:
本文提出PhonemeDF数据集,通过平行真实与合成语音的音素级分割,评估语音合成的自然度与深度伪造检测性能,利用KL散度量化音素分布相似性。
摘要:
随着人工智能生成语音的复杂性增加,音频深度伪造检测面临新挑战。文本到语音(TTS)和语音转换(VC)技术能生成自然且可理解的合成语音,威胁语音生物识别安全及虚假信息传播防控系统。尽管对AI生成语音的兴趣增加,但音素级自然度评估资源有限。本文通过提出Phoneme-Level DeepFake数据集(PhonemeDF),包含平行真实与合成语音的音素级分割。真实语音样本来自LibriSpeech子集,合成样本由四个TTS和三个VC系统生成。使用蒙特利尔强制对齐器(MFA)获取各系统的音素对齐TextGrid文件。通过计算真实与合成音素分布的KL散度(KLD)以量化保真度,并基于与自然语音的相似性建立排名。研究发现KLD与分类器性能之间存在明显相关性,表明KLD可作为深度伪造检测中最具区分性的音素指标。
英文摘要:
The growing sophistication of speech generated by Artificial Intelligence (AI) has introduced new challenges in audio deepfake detection. Text-to-speech (TTS) and voice conversion (VC) technologies can create highly convincing synthetic speech with naturalness and intelligibility. This poses serious threats to voice biometric security and to systems designed to combat the spread of spoken misinformation, where synthetic voices may be used to disseminate false or malicious content. While interest in AI-generated speech has increased, resources for evaluating naturalness at the phoneme level remain limited. In this work, we address this gap by presenting the Phoneme-Level DeepFake dataset (PhonemeDF), comprising parallel real and synthetic speech segmented at the phoneme level. Real speech samples are derived from a subset of LibriSpeech, while synthetic samples are generated using four TTS and three VC systems. For each system, phoneme-aligned TextGrid files are obtained using the Montreal Forced Aligner (MFA). We compute the Kullback-Leibler divergence (KLD) between real and synthetic phoneme distributions to quantify fidelity and establish a ranking based on similarity to natural speech. Our findings show a clear correlation between the KLD of real and synthetic phoneme distributions and the performance of classifiers trained to distinguish them, suggesting that KLD can serve as an indicator of the most discriminative phonemes for deepfake detection.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。