CodecFake:增强反欺骗模型以抵御来自基于编解码器的语音合成系统的 Deepfake 音频
CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems
AI总结:
针对基于编解码器的语音合成系统产生的高逼真 deepfake 音频,本文构建首个 CodecFake 数据集,并证明常用反欺骗模型失效,而该数据集可有效增强其检测能力。
摘要:
当前最先进(SOTA)的基于编解码器的音频合成系统仅需来自特定未见说话人的 3 秒样本,即可模仿任何人的声音。遗憾的是,恶意攻击者可能利用这些技术,造成滥用和安全问题。反欺骗模型已被开发用于检测伪造语音。然而,当前 SOTA 反欺骗模型能否有效对抗来自基于编解码器的语音合成系统的 deepfake 音频,仍是一个尚未解答的开放问题。本文中,我们整理了大量当代 SOTA 编解码器模型,并使用它们重新生成合成语音。这一工作促成了 CodecFake 的创建,它是首个基于编解码器的 deepfake 音频数据集。此外,我们验证了在常用数据集上训练的反欺骗模型无法检测来自当前基于编解码器的语音生成系统的合成语音。所提出的 CodecFake 数据集使这些模型能够有效应对这一挑战。
英文摘要:
Current state-of-the-art (SOTA) codec-based audio synthesis systems can mimic anyone's voice with just a 3-second sample from that specific unseen speaker. Unfortunately, malicious attackers may exploit these technologies, causing misuse and security issues. Anti-spoofing models have been developed to detect fake speech. However, the open question of whether current SOTA anti-spoofing models can effectively counter deepfake audios from codec-based speech synthesis systems remains unanswered. In this paper, we curate an extensive collection of contemporary SOTA codec models, employing them to re-create synthesized speech. This endeavor leads to the creation of CodecFake, the first codec-based deepfake audio dataset. Additionally, we verify that anti-spoofing models trained on commonly used datasets cannot detect synthesized speech from current codec-based speech generation systems. The proposed CodecFake dataset empowers these models to counter this challenge effectively.
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。