AI-generated video has revolutionized short video production, filmmaking, and personalized
media, making video local editing an essential tool. However, this progress also blurs the …

The rapid and wide-scale adoption of AI to generate human speech poses a range of
significant ethical and safety risks to society that need to be addressed. For example, a …

Spectrograms are 2D representations of sound that look very different from the images found
in our visual world. And natural images, when played as spectrograms, make unnatural …

Abstract 3D Gaussian Splatting (3DGS) has already become the emerging research focus in
the fields of 3D scene reconstruction and novel view synthesis. Given that training a 3DGS …

Digital watermarking techniques are crucial for copyright protection and source identification
of images, especially in the era of generative AI models. However, many existing …

In this work, we take on the challenging task of building a single text-to-speech synthesis
system that is capable of generating speech in over 7000 languages, many of which lack …

Automatic detection of synthetic speech is becoming increasingly important as current
synthesis methods are both near indistinguishable from human speech and widely …

Digital watermarking techniques are crucial for copyright protection and source identification
of images, especially in the era of generative AI models. However, many existing …

Amid the burgeoning development of generative models like diffusion models, the task of
differentiating synthesized audio from its natural counterpart grows more daunting …

As the outputs of generative AI (GenAI) techniques improve in quality, it becomes
increasingly challenging to distinguish them from human-created content. Watermarking …