Sep 25, 2019 · Abstract: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 repre- sent a human-acceptable distribution that is wider than a real-data.

This work formulate a backpropagation-based generator training algorithm by regarding human perception as a black-boxed discriminator and demonstrates that ...

We propose the HumanGAN, a generative adversarial network (GAN) incorporating human perception as a discriminator. A basic GAN trains a generator to ...

Sep 25, 2019 · We propose the HumanGAN, a generative adversarial network (GAN) incorporating human perception as a discriminator. A basic GAN trains a ...

We propose the HumanGAN, a generative adversarial network (GAN) incorporating human perception as a discriminator. A basic GAN trains a generator to ...

The HumanGAN [6] was proposed to represent the human-acceptable distribution in a wider manner than a real-data distribution. A DNNbased unconditional generator ...

Feb 8, 2021 · ABSTRACT. We propose a conditional generative adversarial network (GAN) in- corporating humans' perceptual evaluations.

Humangan: Generative Adversarial Network With Human-Based Discriminator And Its Evaluation In Speech Perception Modeling ; IEEE MemberUS $11.00 ; Society MemberUS ...

HUMANGAN: GENERATIVE ADVERSARIAL NETWORK WITH HUMAN-BASED DISCRIMINATOR AND ITS EVALUATION IN SPEECH PERCEPTION MODELING. Authors, Kazuki Fujii, National ...