Filters








2 Hits in 2.2 sec

HumanGAN: generative adversarial network with human-based discriminator and its evaluation in speech perception modeling [article]

Kazuki Fujii, Yuki Saito, Shinnosuke Takamichi, Yukino Baba, Hiroshi Saruwatari
2019 arXiv   pre-print
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) [1] is one of the most promising approaches in learning deep generative models.  ... 
arXiv:1909.11391v1 fatcat:57bkdhclxbcqfnvevckdkbghny

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

Yota Ueda, Kazuki Fujii, Yuki Saito, Shinnosuke Takamichi, Yukino Baba, Hiroshi Saruwatari
2021
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