Related papers: HQ-MPSD: A Multilingual Artifact-Controlled Benchm…
Partially manipulating a sentence can greatly change its meaning. Recent work shows that countermeasures (CMs) trained on partially spoofed audio can effectively detect such spoofing. However, the current understanding of the…
The rapid growth of the digital economy in South-East Asia (SEA) has amplified the risks of audio deepfakes, yet current datasets cover SEA languages only sparsely, leaving models poorly equipped to handle this critical region. This…
All existing databases of spoofed speech contain attack data that is spoofed in its entirety. In practice, it is entirely plausible that successful attacks can be mounted with utterances that are only partially spoofed. By definition,…
Detecting partial deepfake speech is essential due to its potential for subtle misinformation. However, existing methods depend on costly frame-level annotations during training, limiting real-world scalability. Also, they focus on…
Existing fake audio detection systems perform well in in-domain testing, but still face many challenges in out-of-domain testing. This is due to the mismatch between the training and test data, as well as the poor generalizability of…
The availability of highly convincing audio deepfake generators highlights the need for designing robust audio deepfake detectors. Existing works often rely solely on real and fake data available in the training set, which may lead to…
This paper conducts a comprehensive layer-wise analysis of self-supervised learning (SSL) models for audio deepfake detection across diverse contexts, including multilingual datasets (English, Chinese, Spanish), partial, song, and…
Recent advances in deep learning and computer vision have made the synthesis and counterfeiting of multimedia content more accessible than ever, leading to possible threats and dangers from malicious users. In the audio field, we are…
The rise of singing voice synthesis presents critical challenges to artists and industry stakeholders over unauthorized voice usage. Unlike synthesized speech, synthesized singing voices are typically released in songs containing strong…
Speech separation is very important in real-world applications such as human-machine interaction, hearing aids devices, and automatic meeting transcription. In recent years, a significant improvement occurred towards the solution based on…
Deepfake detection automatically recognizes the manipulated medias through the analysis of the difference between manipulated and non-altered videos. It is natural to ask which are the top performers among the existing deepfake detection…
Audio deepfakes pose a growing threat, already exploited in fraud and misinformation. A key challenge is ensuring detectors remain robust to unseen synthesis methods and diverse speakers, since generation techniques evolve quickly. Despite…
With the development of audio deepfake techniques, attacks with partially deepfake audio are beginning to rise. Compared to fully deepfake, it is much harder to be identified by the detector due to the partially cryptic manipulation,…
Deepfake speech detection systems are often limited to binary classification tasks and struggle to generate interpretable reasoning or provide context-rich explanations for their decisions. These models primarily extract latent embeddings…
The Automatic Speaker Verification (ASV) system is vulnerable to fraudulent activities using audio deepfakes, also known as logical-access voice spoofing attacks. These deepfakes pose a concerning threat to voice biometrics due to recent…
The existing audio datasets are predominantly tailored towards single languages, overlooking the complex linguistic behaviors of multilingual communities that engage in code-switching. This practice, where individuals frequently mix two or…
Partially spoofed audio detection is a challenging task, lying in the need to accurately locate the authenticity of audio at the frame level. To address this issue, we propose a fine-grained partially spoofed audio detection method, namely…
With the rise of generative text-to-speech models, distinguishing between real and synthetic speech has become challenging, especially for Arabic that have received limited research attention. Most spoof detection efforts have focused on…
Automated hate speech detection is an important tool in combating the spread of hate speech, particularly in social media. Numerous methods have been developed for the task, including a recent proliferation of deep-learning based…
Deep generative modeling has the potential to cause significant harm to society. Recognizing this threat, a magnitude of research into detecting so-called "Deepfakes" has emerged. This research most often focuses on the image domain, while…