Related papers: DFADD: The Diffusion and Flow-Matching Based Audio…
The diffusion model is capable of generating high-quality data through a probabilistic approach. However, it suffers from the drawback of slow generation speed due to the requirement of a large number of time steps. To address this…
Singing voice synthesis and singing voice conversion have significantly advanced, revolutionizing musical experiences. However, the rise of "Deepfake Songs" generated by these technologies raises concerns about authenticity. Unlike Audio…
This paper introduces SpoofCeleb, a dataset designed for Speech Deepfake Detection (SDD) and Spoofing-robust Automatic Speaker Verification (SASV), utilizing source data from real-world conditions and spoofing attacks generated by…
RuASD (Russian AntiSpoofing Dataset) is a dedicated, reproducible benchmark for Russian-language speech anti-spoofing designed to evaluate both in-domain discrimination and robustness to deployment-style distribution shifts. It combines a…
As audio deepfakes transition from research artifacts to widely available commercial tools, robust biometric authentication faces pressing security threats in high-stakes industries. This paper presents a systematic empirical evaluation of…
The diffusion models including Denoising Diffusion Probabilistic Models (DDPM) and score-based generative models have demonstrated excellent performance in speech synthesis tasks. However, its effectiveness comes at the cost of numerous…
Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthesis. This paper…
The rapid progress of Deepfake technology has made face swapping highly realistic, raising concerns about the malicious use of fabricated facial content. Existing methods often struggle to generalize to unseen domains due to the diverse…
Synthetic data generation is an important tool for privacy-preserving data sharing. Although diffusion models have set recent benchmarks, flow matching (FM) offers a promising alternative. This paper presents different ways to implement FM…
Despite imperfect score-matching causing drift in training and sampling distributions of diffusion models, recent advances in diffusion-based acoustic models have revolutionized data-sufficient single-speaker Text-to-Speech (TTS)…
We present SALAD, a zero-shot TTS autoregressive model operating over continuous speech representations. SALAD utilizes a per-token diffusion process to refine and predict continuous representations for the next time step. We compare our…
Audio generation systems now create very realistic soundscapes that can enhance media production, but also pose potential risks. Several studies have examined deepfakes in speech or singing voice. However, environmental sounds have…
Video and audio are closely correlated modalities that humans naturally perceive together. While recent advancements have enabled the generation of audio or video from text, producing both modalities simultaneously still typically relies on…
Audio super-resolution is challenging owing to its ill-posed nature. Recently, the application of diffusion models in audio super-resolution has shown promising results in alleviating this challenge. However, diffusion-based models have…
Speech deepfake detection has achieved remarkable success in clean environments but faces significant challenges in complex, real-world scenarios where speech is often mixed with background music or noise. Current state-of-the-art methods…
The rapid progress in deep learning has given rise to hyper-realistic facial forgery methods, leading to concerns related to misinformation and security risks. Existing face forgery datasets have limitations in generating high-quality…
Recently, the application of diffusion models has facilitated the significant development of speech and audio generation. Nevertheless, the quality of samples generated by diffusion models still needs improvement. And the effectiveness of…
Speech synthesis systems can now produce highly realistic vocalisations that pose significant authenticity challenges. Despite substantial progress in deepfake detection models, their real-world effectiveness is often undermined by evolving…
Flow-matching models have enabled high-quality text-to-speech synthesis, but their iterative sampling process during inference incurs substantial computational cost. Although distillation is widely used to reduce the number of inference…
We show how replay attacks undermine audio deepfake detection: By playing and re-recording deepfake audio through various speakers and microphones, we make spoofed samples appear authentic to the detection model. To study this phenomenon in…