English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

We propose a conditional generative adversarial network (GAN) incorporatinghumans' perceptual evaluations. A deep neural network (DNN)-based generator ofa GAN can represent a real-data distribution accurately but can never representa human-acceptable distribution, which are ranges of data in which humansaccept the naturalness regardless of whether the data are real or not. AHumanGAN was proposed to model the human-acceptable distribution. A DNN-basedgenerator 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 proposesthe HumanACGAN, a theoretical extension of the HumanGAN, to deal withconditional human-acceptable distributions. Our HumanACGAN trains a DNN-basedconditional generator by regarding humans as not only a discriminator but alsoan auxiliary classifier. The generator is trained by deceiving the human-baseddiscriminator that scores the unconditioned naturalness and the human-basedclassifier that scores the class-conditioned perceptual acceptability. Thetraining can be executed using the backpropagation algorithm involving humans'perceptual evaluations. Our experimental results in phoneme perceptiondemonstrate that our HumanACGAN can successfully train this conditionalgenerator.

HumanACGAN: conditional generative adversarial network with human-based auxiliary classifier and its evaluation in phoneme perception