A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is
We propose the HumanGAN, a generative adversarial network (GAN) incorporating human perception as a discriminator. ... We evaluate our HumanGAN in speech naturalness modeling and demonstrate that it can represent a human-acceptable distribution that is wider than a real-data distribution. ... A generative adversarial network (GAN)  is one of the most promising approaches in learning deep generative models. ...arXiv:1909.11391v1 fatcat:57bkdhclxbcqfnvevckdkbghny
We propose a conditional generative adversarial network (GAN) incorporating humans' perceptual evaluations. ... A DNN-based generator is trained using a human-based discriminator, i.e., humans' perceptual evaluations, instead of the GAN's DNN-based discriminator. ... Our HumanACGAN replaces both the DNN-based discriminator and auxiliary classifier with humans. The HumanACGAN's generator is trained using human-perception-based discrimination and classification. ...doi:10.48550/arxiv.2102.04051 fatcat:kdtjat25ibhnrlilxmw5jzg56y