相关论文: SceneFake: An Initial Dataset and Benchmarks for S…

Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision. However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained…

Good datasets are essential for developing and benchmarking any machine learning system. Their importance is even more extreme for safety critical applications such as deepfake detection - the focus of this paper. Here we reveal that two of…

Automatic speaker verification (ASV) systems utilize the biometric information in human speech to verify the speaker's identity. The techniques used for performing speaker verification are often vulnerable to malicious attacks that attempt…

Parallel to the development of advanced deepfake audio generation, audio deepfake detection has also seen significant progress. However, a standardized and comprehensive benchmark is still missing. To address this, we introduce Speech…

Audio deepfake detection (ADD) is essential for preventing the misuse of synthetic voices that may infringe on personal rights and privacy. Recent zero-shot text-to-speech (TTS) models pose higher risks as they can clone voices with a…

Detecting synthetic from real speech is increasingly crucial due to the risks of misinformation and identity impersonation. While various datasets for synthetic speech analysis have been developed, they often focus on specific areas,…

Speech deepfakes are artificial voices generated by machine learning models. Previous literature has highlighted deepfakes as one of the biggest security threats arising from progress in artificial intelligence due to their potential for…

With the rapid advancement of generative audio models, distinguishing between human-composed and generated music is becoming increasingly challenging. As a response, models for detecting fake music have been proposed. In this work, we…

Detecting partial deepfake speech is challenging because manipulations occur only in short regions while the surrounding audio remains authentic. However, existing detection methods are fundamentally limited by the quality of available…

ASVspoof 5 is the fifth edition in a series of challenges that promote the study of speech spoofing and deepfake attacks, and the design of detection solutions. Compared to previous challenges, the ASVspoof 5 database is built from…

Audio deepfake detection aims to detect real human voices from those generated by Artificial Intelligence (AI) and has emerged as a significant problem in the field of voice biometrics systems. With the ever-improving quality of synthetic…

Deepfake is content or material that is synthetically generated or manipulated using artificial intelligence (AI) methods, to be passed off as real and can include audio, video, image, and text synthesis. This survey has been conducted with…

Advancements in AI-synthesized human voices have created a growing threat of impersonation and disinformation, making it crucial to develop methods to detect synthetic human voices. This study proposes a new approach to identifying…

Spoofed utterances always contain artifacts introduced by generative models. While several countermeasures have been proposed to detect spoofed utterances, most primarily focus on architectural improvements. In this work, we investigate how…

Deepfakes, synthetic media created using advanced AI techniques, pose a growing threat to information integrity, particularly in politically sensitive contexts. This challenge is amplified by the increasing realism of modern generative…

The detection and localization of highly realistic deepfake audio-visual content are challenging even for the most advanced state-of-the-art methods. While most of the research efforts in this domain are focused on detecting high-quality…

The rapid spread of media content synthesis technology and the potentially damaging impact of audio and video deepfakes on people's lives have raised the need to implement systems able to detect these forgeries automatically. In this work…

Spoofed audio, i.e. audio that is manipulated or AI-generated deepfake audio, is difficult to detect when only using acoustic features. Some recent innovative work involving AI-spoofed audio detection models augmented with phonetic and…

Audio-language models (ALMs) generate linguistic descriptions of sound-producing events and scenes. Advances in dataset creation and computational power have led to significant progress in this domain. This paper surveys 69 datasets used to…

Deepfake speech utterances can be forged by replacing one or more words in a bona fide utterance with semantically different words synthesized with speech-generative models. While a dedicated synthetic word detector could be developed, we…