Related papers: Codecfake: An Initial Dataset for Detecting LLM-ba…
Recent attempts at source tracing for codec-based deepfake speech (CodecFake), generated by neural audio codec-based speech generation (CoSG) models, have exhibited suboptimal performance. However, how to train source tracing models using…
Many datasets have been designed to further the development of fake audio detection, such as datasets of the ASVspoof and ADD challenges. However, these datasets do not consider a situation that the emotion of the audio has been changed…
The generalization of Fake Audio Detection (FAD) is critical due to the emergence of new spoofing techniques. Traditional FAD methods often focus solely on distinguishing between genuine and known spoofed audio. We propose a Genuine-Focused…
The rise of advanced large language models such as GPT-4, GPT-4o, and the Claude family has made fake audio detection increasingly challenging. Traditional fine-tuning methods struggle to keep pace with the evolving landscape of synthetic…
Foley sound generation, the art of creating audio for multimedia, has recently seen notable advancements through text-conditioned latent diffusion models. These systems use multimodal text-audio representation models, such as Contrastive…
While the technologies empowering malicious audio deepfakes have dramatically evolved in recent years due to generative AI advances, the same cannot be said of global research into spoofing (deepfake) countermeasures. This paper highlights…
The existing fake audio detection systems often rely on expert experience to design the acoustic features or manually design the hyperparameters of the network structure. However, artificial adjustment of the parameters can have a…
Audio Deepfake Detection (ADD) aims to detect the fake audio generated by text-to-speech (TTS), voice conversion (VC) and replay, etc., which is an emerging topic. Traditionally we take the mono signal as input and focus on robust feature…
The rapid rise of deepfake technology poses a severe threat to social and political stability by enabling hyper-realistic synthetic media capable of manipulating public perception. However, existing detection methods struggle with two core…
This paper describes our submitted systems to the ASVspoof 5 Challenge Track 1: Speech Deepfake Detection - Open Condition, which consists of a stand-alone speech deepfake (bonafide vs spoof) detection task. Recently, large-scale…
Recently, the AI community has made significant strides in developing powerful foundation models, driven by large-scale multimodal datasets. However, for audio representation learning, existing datasets suffer from limitations in the…
Deep neural networks have recently achieved breakthroughs in sound generation. Despite the outstanding sample quality, current sound generation models face issues on small-scale datasets (e.g., overfitting), significantly limiting…
With the rapid growth in deepfake video content, we require improved and generalizable methods to detect them. Most existing detection methods either use uni-modal cues or rely on supervised training to capture the dissonance between the…
With the rising prevalence of deepfakes, there is a growing interest in developing generalizable detection methods for various types of deepfakes. While effective in their specific modalities, traditional detection methods fall short in…
Language model (LM) based audio generation frameworks, e.g., AudioLM, have recently achieved new state-of-the-art performance in zero-shot audio generation. In this paper, we explore the feasibility of LMs for zero-shot voice conversion. An…
Text-to-Speech (TTS) and Voice Conversion (VC) models have exhibited remarkable performance in generating realistic and natural audio. However, their dark side, audio deepfake poses a significant threat to both society and individuals.…
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 SAFE Challenge evaluates synthetic speech detection across three tasks: unmodified audio, processed audio with compression artifacts, and laundered audio designed to evade detection. We systematically explore self-supervised learning…
Existing methods for deepfake audio detection have demonstrated some effectiveness. However, they still face challenges in generalizing to new forgery techniques and evolving attack patterns. This limitation mainly arises because the models…
Fake audio attack becomes a major threat to the speaker verification system. Although current detection approaches have achieved promising results on dataset-specific scenarios, they encounter difficulties on unseen spoofing data.…