HTML has supported multimedia elements—images, video, audio—for many decades, but the latter two required browser plugins ...

Abstract: Controllable generation in StyleGANs is usually achieved by training the model using labeled data. For audio textures, however, there is currently a lack of large semantically labeled ...

Abstract: With the widespread application of automatic speech recognition (ASR) systems, their vulnerability to adversarial attacks has been extensively studied. However, most existing adversarial ...