CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
SafeSpeech: Robust and Universal Voice Protection Against Malicious Speech Synthesis
ArVoice: A Multi-Speaker Dataset for Arabic Speech Synthesis
DPN-GAN: Inducing Periodic Activations in Generative Adversarial Networks for High-Fidelity Audio Synthesis
ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech
XAttnMark: Learning Robust Audio Watermarking with Cross-Attention
Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.