...Jen-Tzung Chien; Yuan-An Chen A learning machine is prone to be attacked by adversarial examples contaminated by perturbations. Adversarial training ( AT ) is developed to build a defense model against adversarial attacks. Most of previous works were conducted in supervised setting. To release...

... and authors. The full terms of this licence may be seen at Link to the terms of the CC BY-NC 4.0 licence . Dialogue system Empathy Adversarial training In recent decades, spoken dialogue systems have gained popularity among those seeking additional assistance and have been extensively...

... purposes only), subject to full attribution to the original publication and authors. The full terms of this licence may be seen at Link to the terms of the CC BY-NC 4.0 licence . Deep learning unsupervised domain adaptation transfer learning adversarial training self training Deep...