Source Tracing of Audio Deepfake Systems
원문 초록
Recent progress in generative AI technology has made audio deepfakes remarkably more realistic. While current research on anti-spoofing systems primarily focuses on assessing whether a given audio sample is fake or genuine, there has been limited attention on discerning the specific techniques to create the audio deepfakes. Algorithms commonly used in audio deepfake generation, like text-to-speech (TTS) and voice conversion (VC), undergo distinct stages including input processing, acoustic modeling, and waveform generation. In this work, we introduce a system designed to classify various spoofing attributes, capturing the distinctive features of individual modules throughout the entire generation pipeline. We evaluate our system on two datasets: the ASVspoof 2019 Logical Access and the Multi-Language Audio Anti-Spoofing Dataset (MLAAD). Results from both experiments demonstrate the robustness of the system to identify the different spoofing attributes of deepfake generation systems.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Few-Shot Speech Deepfake Detection Adaptation with Gaussian Processes
BanglaFake: Constructing and Evaluating a Specialized Bengali Deepfake Audio Dataset
SALF-MOS: Speaker Agnostic Latent Features Downsampled for MOS Prediction
What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection
Bts-e: Audio deepfake detection using breathing-talking-silence encoder
ZipVoice-Dialog: Non-Autoregressive Spoken Dialogue Generation with Flow Matching
토론
이 논문과 연결된 포럼 글이 아직 없습니다.