HumanACGAN：基于人的辅助分类器的条件生成对抗网络及其在音素感知中的评价
HumanACGAN: conditional generative adversarial network with human-based auxiliary classifier and its evaluation in phoneme perception
摘要：
我们提出了一个条件生成对抗网络（GAN），结合人类的感知评价。基于深度神经网络（DNN）的GAN生成器可以准确地表示真实数据分布，但永远无法表示人类可接受的分布，这些分布是人类接受自然性的数据范围，而不管数据是否真实。提出了一个HumanGAN来模拟人类可接受的分布。基于DNN的生成器使用基于人类的训练器来训练，即，人类的感知评估，而不是GAN的基于DNN的评估。但是，HumanGAN不能表示条件分布。本文提出了HumanACGAN，HumanGAN的理论扩展，处理条件人类可接受的分布。我们的HumanACGAN通过将人类不仅视为机器人，而且还视为辅助分类器来训练基于DNN的条件生成器。该生成器通过欺骗基于人类的分类器和基于人类的分类器来训练，其中基于人类的分类器对无条件自然性进行评分，基于人类的分类器对类条件感知可接受性进行评分。训练可以使用涉及人类感知评估的反向传播算法来执行。我们在音素感知上的实验结果表明，我们的HumanACGAN可以成功地训练这个条件生成器。
英文摘要：
We propose a conditional generative adversarial network (GAN) incorporating humans' perceptual evaluations. A deep neural network (DNN)-based generator of a GAN can represent a real-data distribution accurately but can never represent a human-acceptable distribution, which are ranges of data in which humans accept the naturalness regardless of whether the data are real or not. A HumanGAN was proposed to model the human-acceptable distribution. A DNN-based generator is trained using a human-based discriminator, i.e., humans' perceptual evaluations, instead of the GAN's DNN-based discriminator. However, the HumanGAN cannot represent conditional distributions. This paper proposes the HumanACGAN, a theoretical extension of the HumanGAN, to deal with conditional human-acceptable distributions. Our HumanACGAN trains a DNN-based conditional generator by regarding humans as not only a discriminator but also an auxiliary classifier. The generator is trained by deceiving the human-based discriminator that scores the unconditioned naturalness and the human-based classifier that scores the class-conditioned perceptual acceptability. The training can be executed using the backpropagation algorithm involving humans' perceptual evaluations. Our experimental results in phoneme perception demonstrate that our HumanACGAN can successfully train this conditional generator.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
