Diffuse Or Confuse: A Diffusion Deepfake Speech Dataset

Abstract

Advancements in artificial intelligence and machine learning have significantly improved synthetic speech generation. This paper explores diffusion models, a novel method for creating realistic synthetic speech. We create a diffusion dataset using available tools and pretrained models. Additionally, this study assesses the quality of diffusion-generated deepfakes versus non-diffusion ones and their potential threat to current deepfake detection systems. Findings indicate that the detection of diffusion-based deepfakes is generally comparable to non-diffusion deepfakes, with some variability based on detector architecture. Re-vocoding with diffusion vocoders shows minimal impact, and the overall speech quality is comparable to non-diffusion methods.

Stats

• citations4
• S2 citations—
• github stars0
• HF likes0
• heat score5.24
• arxiv keyfirc2024diffuse

Related papers

• Facediffuser: Speech-driven 3D Facial Animation Synthesis Using Diffusion (2023)13.79
• A Survey On Speech Deepfake Detection (2024)12.10
• Diffmotion: Speech-driven Gesture Synthesis Using Denoising Diffusion Model (2023)9.59
• AUDETER: A Large-scale Dataset For Deepfake Audio Detection In Open Worlds (2025)0.00
• Diffspeaker: Speech-driven 3D Facial Animation With Diffusion Transformer (2024)5.24
• Extract And Diffuse: Latent Integration For Improved Diffusion-based Speech And Vocal Enhancement (2024)0.00
• Diffar: Denoising Diffusion Autoregressive Model For Raw Speech Waveform Generation (2023)0.00
• Fastdiff: A Fast Conditional Diffusion Model For High-quality Speech Synthesis (2022)14.35